Spaces:

SimWorld-AI
/

Code4Scene

Running

App Files Files Community

KoeYe Claude Opus 5.5 commited on 27 days ago

Commit

391a498

verified ·

1 Parent(s): 0c7052b

Text-to-Scene: Gemma 4 31B (thinking on) cost estimated from its logged tokens

Browse files

Gemma 4 31B ran on self-hosted weights, so nothing was billed. Its cost is now the token counts its agent logged on every model call (scripts/t2s_token_cost.py) at Gemma 4 31B's OpenRouter list price ($0.20 input, $0.40 output per million): median $0.056 per case, shown as $0.06*, with the basis in the table, tooltips, Pareto caption and gallery. It now has a Pareto point, on the frontier.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

Files changed (10) hide show

README.md +6 -2
data/leaderboard-details.json +2 -2
data/pareto.json +8 -0
data/t2s-sandbox.json +24 -24
gallery/cases.html +0 -0
gallery/index.html +1 -1
gallery/model/gemma-4-31b-thinking-on.html +0 -0
index.html +0 -0
scripts/t2s_sandbox_round.py +4 -0
scripts/t2s_token_cost.py +54 -0

README.md CHANGED Viewed

@@ -34,8 +34,11 @@ paper's evaluation; the Takeaways and the explorer say so.
   0.2 × Detailed + 0.6 × Overview + 0.2 × Physical; a case without a valid scene scores 0; the model's score is the mean.
   As on the internal leaderboard, scores are never rounded up (bar labels ×100 rounded down, table values truncated to
   three decimals) and cost is the median USD per case, to the cent. An agent that records no token usage, or a run on
-  self-hosted weights (nothing billed: Gemma 4 31B), has no cost and no Pareto point; the table, tooltips, Pareto caption
-  and gallery say which.
 - Snapshots: 2026-10-16 06:21 UTC (15 configurations); 2026-10-16 16:01 UTC (19: GPT-6 Luna, Muse Spark Open, MiMo V2.6
   Pro and Gemma 4 31B (thinking on) finished; Inkling had not started scoring).
 - Xiaomi (MiMo V2.6 Pro) is drawn with Xiaomi's own mark from [Simple Icons](https://simpleicons.org/) (CC0; brand
@@ -60,6 +63,7 @@ Rebuild from a snapshot of the internal Text-to-Scene leaderboard (its served `d
 `scripts/t2s_components.py` extracts with the run-status page's own selection of results:
     ssh <host> python3 - <muse run dirs> < scripts/t2s_muse_cost.py > ../t2s-src/musewf_cost.json
     python3 scripts/t2s_sandbox_round.py --src ../t2s-src [--videos blue-city,ruins,...]
     python3 scripts/t2s_gallery.py --src ../t2s-src

   0.2 × Detailed + 0.6 × Overview + 0.2 × Physical; a case without a valid scene scores 0; the model's score is the mean.
   As on the internal leaderboard, scores are never rounded up (bar labels ×100 rounded down, table values truncated to
   three decimals) and cost is the median USD per case, to the cent. An agent that records no token usage, or a run on
+  self-hosted weights that is not priced, has no cost and no Pareto point; the table, tooltips, Pareto caption and
+  gallery say which.
+- Gemma 4 31B (thinking on) ran on self-hosted weights, so nothing was billed; its cost is the token counts its agent
+  logged on every model call (`scripts/t2s_token_cost.py`, no cached input) at Gemma 4 31B's OpenRouter list price
+  ($0.20 input, $0.40 output per million): median $0.056 per case (user, 2026-10-16).
 - Snapshots: 2026-10-16 06:21 UTC (15 configurations); 2026-10-16 16:01 UTC (19: GPT-6 Luna, Muse Spark Open, MiMo V2.6
   Pro and Gemma 4 31B (thinking on) finished; Inkling had not started scoring).
 - Xiaomi (MiMo V2.6 Pro) is drawn with Xiaomi's own mark from [Simple Icons](https://simpleicons.org/) (CC0; brand
 `scripts/t2s_components.py` extracts with the run-status page's own selection of results:
     ssh <host> python3 - <muse run dirs> < scripts/t2s_muse_cost.py > ../t2s-src/musewf_cost.json
+    ssh <host> python3 - 0.20 0.20 0.40 <gemma run dir> < scripts/t2s_token_cost.py > ../t2s-src/gemma4think_cost.json
     python3 scripts/t2s_sandbox_round.py --src ../t2s-src [--videos blue-city,ruins,...]
     python3 scripts/t2s_gallery.py --src ../t2s-src

data/leaderboard-details.json CHANGED Viewed

@@ -951,8 +951,8 @@
         },
         {
           "label": "Median cost / case",
-          "value": "not billed (self-hosted)",
-          "currency": false
         }
       ]
     },

         },
         {
           "label": "Median cost / case",
+          "value": "0.06",
+          "currency": true
         }
       ]
     },

data/pareto.json CHANGED Viewed

@@ -320,6 +320,14 @@
       "score": 0.527145,
       "cost": 0.921754
     },
     {
       "key": "deepseek-v4.1-flash-max",
       "name": "DeepSeek V4.1 Flash (max)",

       "score": 0.527145,
       "cost": 0.921754
     },
+    {
+      "key": "gemma-4-31b-thinking-on",
+      "name": "Gemma 4 31B (thinking on)",
+      "logo": "gemini",
+      "open": true,
+      "score": 0.51767,
+      "cost": 0.055923
+    },
     {
       "key": "deepseek-v4.1-flash-max",
       "name": "DeepSeek V4.1 Flash (max)",

data/t2s-sandbox.json CHANGED Viewed

@@ -2823,150 +2823,150 @@
    "detailed": 0.44815,
    "overview": 0.469405,
    "physical": 0.73195,
-   "cost": null,
-   "cost_basis": null,
-   "cost_none": "it ran on self-hosted weights, so nothing was billed",
-   "front": false,
    "cases": {
     "abandoned-psychiatric-hospital-long": {
      "score": 0.4496,
      "detailed": 0.4197,
      "overview": 0.3288,
      "physical": 0.8417,
-     "cost": null
     },
     "blue-city-long": {
      "score": 0.6823,
      "detailed": 0.6946,
      "overview": 0.6952,
      "physical": 0.6311,
-     "cost": null
     },
     "castleriver-long": {
      "score": 0.4631,
      "detailed": 0.332,
      "overview": 0.3973,
      "physical": 0.7917,
-     "cost": null
     },
     "cyberpunk-long": {
      "score": 0.5598,
      "detailed": 0.2755,
      "overview": 0.6094,
      "physical": 0.6954,
-     "cost": null
     },
     "egyptian-temple-long": {
      "score": 0.622,
      "detailed": 0.5967,
      "overview": 0.5878,
      "physical": 0.7497,
-     "cost": null
     },
     "european-street-3d-scene-long": {
      "score": 0.4355,
      "detailed": 0.2977,
      "overview": 0.3512,
      "physical": 0.8261,
-     "cost": null
     },
     "factory-environment-long": {
      "score": 0.7606,
      "detailed": 0.7599,
      "overview": 0.7915,
      "physical": 0.6688,
-     "cost": null
     },
     "hong-kong-long": {
      "score": 0.3522,
      "detailed": 0.4756,
      "overview": 0.2938,
      "physical": 0.4038,
-     "cost": null
     },
     "khs-house-of-baeryeom-long": {
      "score": 0.4454,
      "detailed": 0.6185,
      "overview": 0.3583,
      "physical": 0.5337,
-     "cost": null
     },
     "medieval-big-farm-town-long": {
      "score": 0.3974,
      "detailed": 0.3105,
      "overview": 0.3018,
      "physical": 0.7711,
-     "cost": null
     },
     "medieval-buildings-volume-1-long": {
      "score": 0.4887,
      "detailed": 0.6106,
      "overview": 0.3588,
      "physical": 0.7563,
-     "cost": null
     },
     "nordic-harbour-long": {
      "score": 0.6185,
      "detailed": 0.3059,
      "overview": 0.6118,
      "physical": 0.9511,
-     "cost": null
     },
     "paris-long": {
      "score": 0.284,
      "detailed": 0.1343,
      "overview": 0.2098,
      "physical": 0.6564,
-     "cost": null
     },
     "post-apocalyptic-stylized-market-long": {
      "score": 0.7658,
      "detailed": 0.6447,
      "overview": 0.7902,
      "physical": 0.8138,
-     "cost": null
     },
     "ruins-long": {
      "score": 0.2741,
      "detailed": 0.1508,
      "overview": 0.2413,
      "physical": 0.496,
-     "cost": null
     },
     "scifi-environment-offworld-long": {
      "score": 0.6854,
      "detailed": 0.5625,
      "overview": 0.6328,
      "physical": 0.9659,
-     "cost": null
     },
     "street-new-york-long": {
      "score": 0.6885,
      "detailed": 0.6169,
      "overview": 0.6172,
      "physical": 0.9739,
-     "cost": null
     },
     "stylized-elven-valley-long": {
      "score": 0.3875,
      "detailed": 0.4907,
      "overview": 0.3141,
      "physical": 0.5046,
-     "cost": null
     },
     "urban-decay-long": {
      "score": 0.5058,
      "detailed": 0.3245,
      "overview": 0.5289,
      "physical": 0.6176,
-     "cost": null
     },
     "winter-town-long": {
      "score": 0.4872,
      "detailed": 0.3414,
      "overview": 0.3681,
      "physical": 0.9903,
-     "cost": null
     }
    }
   },

    "detailed": 0.44815,
    "overview": 0.469405,
    "physical": 0.73195,
+   "cost": 0.055923,
+   "cost_basis": "self-hosted; cost = the token counts its agent logs, at Gemma 4 31B's OpenRouter list price ($0.20 input, $0.40 output per million)",
+   "cost_none": null,
+   "front": true,
    "cases": {
     "abandoned-psychiatric-hospital-long": {
      "score": 0.4496,
      "detailed": 0.4197,
      "overview": 0.3288,
      "physical": 0.8417,
+     "cost": 0.053845
     },
     "blue-city-long": {
      "score": 0.6823,
      "detailed": 0.6946,
      "overview": 0.6952,
      "physical": 0.6311,
+     "cost": 0.045504
     },
     "castleriver-long": {
      "score": 0.4631,
      "detailed": 0.332,
      "overview": 0.3973,
      "physical": 0.7917,
+     "cost": 0.035562
     },
     "cyberpunk-long": {
      "score": 0.5598,
      "detailed": 0.2755,
      "overview": 0.6094,
      "physical": 0.6954,
+     "cost": 0.073503
     },
     "egyptian-temple-long": {
      "score": 0.622,
      "detailed": 0.5967,
      "overview": 0.5878,
      "physical": 0.7497,
+     "cost": 0.017708
     },
     "european-street-3d-scene-long": {
      "score": 0.4355,
      "detailed": 0.2977,
      "overview": 0.3512,
      "physical": 0.8261,
+     "cost": 0.089901
     },
     "factory-environment-long": {
      "score": 0.7606,
      "detailed": 0.7599,
      "overview": 0.7915,
      "physical": 0.6688,
+     "cost": 0.058232
     },
     "hong-kong-long": {
      "score": 0.3522,
      "detailed": 0.4756,
      "overview": 0.2938,
      "physical": 0.4038,
+     "cost": 0.085658
     },
     "khs-house-of-baeryeom-long": {
      "score": 0.4454,
      "detailed": 0.6185,
      "overview": 0.3583,
      "physical": 0.5337,
+     "cost": 0.055226
     },
     "medieval-big-farm-town-long": {
      "score": 0.3974,
      "detailed": 0.3105,
      "overview": 0.3018,
      "physical": 0.7711,
+     "cost": 0.043655
     },
     "medieval-buildings-volume-1-long": {
      "score": 0.4887,
      "detailed": 0.6106,
      "overview": 0.3588,
      "physical": 0.7563,
+     "cost": 0.032394
     },
     "nordic-harbour-long": {
      "score": 0.6185,
      "detailed": 0.3059,
      "overview": 0.6118,
      "physical": 0.9511,
+     "cost": 0.038948
     },
     "paris-long": {
      "score": 0.284,
      "detailed": 0.1343,
      "overview": 0.2098,
      "physical": 0.6564,
+     "cost": 0.098821
     },
     "post-apocalyptic-stylized-market-long": {
      "score": 0.7658,
      "detailed": 0.6447,
      "overview": 0.7902,
      "physical": 0.8138,
+     "cost": 0.05662
     },
     "ruins-long": {
      "score": 0.2741,
      "detailed": 0.1508,
      "overview": 0.2413,
      "physical": 0.496,
+     "cost": 0.038337
     },
     "scifi-environment-offworld-long": {
      "score": 0.6854,
      "detailed": 0.5625,
      "overview": 0.6328,
      "physical": 0.9659,
+     "cost": 0.027655
     },
     "street-new-york-long": {
      "score": 0.6885,
      "detailed": 0.6169,
      "overview": 0.6172,
      "physical": 0.9739,
+     "cost": 0.078983
     },
     "stylized-elven-valley-long": {
      "score": 0.3875,
      "detailed": 0.4907,
      "overview": 0.3141,
      "physical": 0.5046,
+     "cost": 0.062948
     },
     "urban-decay-long": {
      "score": 0.5058,
      "detailed": 0.3245,
      "overview": 0.5289,
      "physical": 0.6176,
+     "cost": 0.253754
     },
     "winter-town-long": {
      "score": 0.4872,
      "detailed": 0.3414,
      "overview": 0.3681,
      "physical": 0.9903,
+     "cost": 0.07376
     }
    }
   },

gallery/cases.html CHANGED Viewed

The diff for this file is too large to render. See raw diff

gallery/index.html CHANGED Viewed

@@ -9,7 +9,7 @@
 </head><body class="gallery-page"><a class="skip-link" href="#main">Skip to the gallery</a>
 <header class="site-header"><div class="brand"><a aria-label="Code4Scene home" class="brand-home" href="../index.html#top"><svg aria-hidden="true" fill="none" viewbox="0 0 30 32"><path d="M15 2 27 9v14l-12 7L3 23V9L15 2Z M3 9l12 7 12-7 M15 16v14 M9 5.5l12 7v14 M21 5.5l-12 7v14" stroke="currentColor" stroke-linejoin="round" stroke-width="1.6"></path></svg><span>Code4Scene</span></a><a class="brand-by" href="https://simworld.org/">by SimWorld</a></div><nav aria-label="Main navigation"><a href="../index.html#top">Benchmark</a><a href="../index.html#leaderboard">Leaderboard</a><a href="../index.html#cases">Visualization</a><a class="nav-active" href="../gallery/index.html">Gallery</a><a href="https://arxiv.org/abs/2609.36777" rel="noopener" target="_blank">Paper ↗</a><a href="https://github.com/SimWorld-AI/Code4Scene" rel="noopener" target="_blank">Github ↗</a></nav></header>
 <main class="page-main" id="main">
-<section class="gal-top"><div class="container"><span class="section-label">Gallery</span><h1 class="section-title">Every scene, every agent</h1><p class="section-desc">What each configuration built on the 20 Research Track scenes in the October 2026 Text-to-Scene re-run, as the evaluator saw it: four renders per scene from the benchmark&#x27;s own cameras, with the case score and the agent&#x27;s cost. Scores are truncated to three decimals; a case without a valid scene scores 0.</p><nav aria-label="Browse the gallery" class="gal-switch"><a aria-current="page" class="on" href="index.html">By agent</a><a href="cases.html">By scene</a></nav></div></section><section class="gal-body"><div class="container"><p class="gal-note">In leaderboard order. The strip shows the same five scenes for every agent: Blue City, Cyberpunk, Egyptian Temple, Nordic Harbour, Winter Town.</p><ol class="gal-agents"><li><a class="gal-agent" href="model/claude-sonnet-5.5-max.html"><span class="rk">1</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#D97757" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Claude</title><path d="M4.709 15.955l4.72-2.647.08-.23-.08-.128H9.2l-.79-.048-2.698-.073-2.339-.097-2.266-.122-.571-.121L0 11.784l.055-.352.48-.321.686.06 1.52.103 2.278.158 1.652.097 2.449.255h.389l.055-.157-.134-.098-.103-.097-2.358-1.596-2.552-1.688-1.336-.972-.724-.491-.364-.462-.158-1.008.656-.722.881.06.225.061.893.686 1.908 1.476 2.491 1.833.365.304.145-.103.019-.073-.164-.274-1.355-2.446-1.446-2.49-.644-1.032-.17-.619a2.97 2.97 0 01-.104-.729L6.283.134 6.696 0l.996.134.42.364.62 1.414 1.002 2.229 1.555 3.03.456.898.243.832.091.255h.158V9.01l.128-1.706.237-2.095.23-2.695.08-.76.376-.91.747-.492.584.28.48.685-.067.444-.286 1.851-.559 2.903-.364 1.942h.212l.243-.242.985-1.306 1.652-2.064.73-.82.85-.904.547-.431h1.033l.76 1.129-.34 1.166-1.064 1.347-.881 1.142-1.264 1.7-.79 1.36.073.11.188-.02 2.856-.606 1.543-.28 1.841-.315.833.388.091.395-.328.807-1.969.486-2.309.462-3.439.813-.042.03.049.061 1.549.146.662.036h1.622l3.02.225.79.522.474.638-.079.485-1.215.62-1.64-.389-3.829-.91-1.312-.329h-.182v.11l1.093 1.068 2.006 1.81 2.509 2.33.127.578-.322.455-.34-.049-2.205-1.657-.851-.747-1.926-1.62h-.128v.17l.444.649 2.345 3.521.122 1.08-.17.353-.608.213-.668-.122-1.374-1.925-1.415-2.167-1.143-1.943-.14.08-.674 7.254-.316.37-.729.28-.607-.461-.322-.747.322-1.476.389-1.924.315-1.53.286-1.9.17-.632-.012-.042-.14.018-1.434 1.967-2.18 2.945-1.726 1.845-.414.164-.717-.37.067-.662.401-.589 2.388-3.036 1.44-1.882.93-1.086-.006-.158h-.055L4.132 18.56l-1.13.146-.487-.456.061-.746.231-.243 1.908-1.312-.006.006z"></path></svg></span><span><b>Claude Sonnet 5.5 (max)</b><small>Anthropic</small></span></span><span class="num"><small>Score</small><b>0.837</b></span><span class="num"><small>Median cost</small>$26.93</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-sonnet-5.5-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-sonnet-5.5-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-sonnet-5.5-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-sonnet-5.5-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-sonnet-5.5-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/claude-opus-5.5-max.html"><span class="rk">2</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#D97757" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Claude</title><path d="M4.709 15.955l4.72-2.647.08-.23-.08-.128H9.2l-.79-.048-2.698-.073-2.339-.097-2.266-.122-.571-.121L0 11.784l.055-.352.48-.321.686.06 1.52.103 2.278.158 1.652.097 2.449.255h.389l.055-.157-.134-.098-.103-.097-2.358-1.596-2.552-1.688-1.336-.972-.724-.491-.364-.462-.158-1.008.656-.722.881.06.225.061.893.686 1.908 1.476 2.491 1.833.365.304.145-.103.019-.073-.164-.274-1.355-2.446-1.446-2.49-.644-1.032-.17-.619a2.97 2.97 0 01-.104-.729L6.283.134 6.696 0l.996.134.42.364.62 1.414 1.002 2.229 1.555 3.03.456.898.243.832.091.255h.158V9.01l.128-1.706.237-2.095.23-2.695.08-.76.376-.91.747-.492.584.28.48.685-.067.444-.286 1.851-.559 2.903-.364 1.942h.212l.243-.242.985-1.306 1.652-2.064.73-.82.85-.904.547-.431h1.033l.76 1.129-.34 1.166-1.064 1.347-.881 1.142-1.264 1.7-.79 1.36.073.11.188-.02 2.856-.606 1.543-.28 1.841-.315.833.388.091.395-.328.807-1.969.486-2.309.462-3.439.813-.042.03.049.061 1.549.146.662.036h1.622l3.02.225.79.522.474.638-.079.485-1.215.62-1.64-.389-3.829-.91-1.312-.329h-.182v.11l1.093 1.068 2.006 1.81 2.509 2.33.127.578-.322.455-.34-.049-2.205-1.657-.851-.747-1.926-1.62h-.128v.17l.444.649 2.345 3.521.122 1.08-.17.353-.608.213-.668-.122-1.374-1.925-1.415-2.167-1.143-1.943-.14.08-.674 7.254-.316.37-.729.28-.607-.461-.322-.747.322-1.476.389-1.924.315-1.53.286-1.9.17-.632-.012-.042-.14.018-1.434 1.967-2.18 2.945-1.726 1.845-.414.164-.717-.37.067-.662.401-.589 2.388-3.036 1.44-1.882.93-1.086-.006-.158h-.055L4.132 18.56l-1.13.146-.487-.456.061-.746.231-.243 1.908-1.312-.006.006z"></path></svg></span><span><b>Claude Opus 5.5 (max)</b><small>Anthropic</small></span></span><span class="num"><small>Score</small><b>0.832</b></span><span class="num"><small>Median cost</small>$26.90</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-opus-5.5-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-opus-5.5-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-opus-5.5-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-opus-5.5-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-opus-5.5-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/claude-fable-5.1-max.html"><span class="rk">3</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#D97757" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Claude</title><path d="M4.709 15.955l4.72-2.647.08-.23-.08-.128H9.2l-.79-.048-2.698-.073-2.339-.097-2.266-.122-.571-.121L0 11.784l.055-.352.48-.321.686.06 1.52.103 2.278.158 1.652.097 2.449.255h.389l.055-.157-.134-.098-.103-.097-2.358-1.596-2.552-1.688-1.336-.972-.724-.491-.364-.462-.158-1.008.656-.722.881.06.225.061.893.686 1.908 1.476 2.491 1.833.365.304.145-.103.019-.073-.164-.274-1.355-2.446-1.446-2.49-.644-1.032-.17-.619a2.97 2.97 0 01-.104-.729L6.283.134 6.696 0l.996.134.42.364.62 1.414 1.002 2.229 1.555 3.03.456.898.243.832.091.255h.158V9.01l.128-1.706.237-2.095.23-2.695.08-.76.376-.91.747-.492.584.28.48.685-.067.444-.286 1.851-.559 2.903-.364 1.942h.212l.243-.242.985-1.306 1.652-2.064.73-.82.85-.904.547-.431h1.033l.76 1.129-.34 1.166-1.064 1.347-.881 1.142-1.264 1.7-.79 1.36.073.11.188-.02 2.856-.606 1.543-.28 1.841-.315.833.388.091.395-.328.807-1.969.486-2.309.462-3.439.813-.042.03.049.061 1.549.146.662.036h1.622l3.02.225.79.522.474.638-.079.485-1.215.62-1.64-.389-3.829-.91-1.312-.329h-.182v.11l1.093 1.068 2.006 1.81 2.509 2.33.127.578-.322.455-.34-.049-2.205-1.657-.851-.747-1.926-1.62h-.128v.17l.444.649 2.345 3.521.122 1.08-.17.353-.608.213-.668-.122-1.374-1.925-1.415-2.167-1.143-1.943-.14.08-.674 7.254-.316.37-.729.28-.607-.461-.322-.747.322-1.476.389-1.924.315-1.53.286-1.9.17-.632-.012-.042-.14.018-1.434 1.967-2.18 2.945-1.726 1.845-.414.164-.717-.37.067-.662.401-.589 2.388-3.036 1.44-1.882.93-1.086-.006-.158h-.055L4.132 18.56l-1.13.146-.487-.456.061-.746.231-.243 1.908-1.312-.006.006z"></path></svg></span><span><b>Claude Fable 5.1 (max)</b><small>Anthropic</small></span></span><span class="num"><small>Score</small><b>0.800</b></span><span class="num"><small>Median cost</small>$23.42</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-fable-5.1-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-fable-5.1-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-fable-5.1-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-fable-5.1-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-fable-5.1-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gpt-6-astra-max.html"><span class="rk">4</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>OpenAI</title><path d="M9.205 8.658v-2.26c0-.19.072-.333.238-.428l4.543-2.616c.619-.357 1.356-.523 2.117-.523 2.854 0 4.662 2.212 4.662 4.566 0 .167 0 .357-.024.547l-4.71-2.759a.797.797 0 00-.856 0l-5.97 3.473zm10.609 8.8V12.06c0-.333-.143-.57-.429-.737l-5.97-3.473 1.95-1.118a.433.433 0 01.476 0l4.543 2.617c1.309.76 2.189 2.378 2.189 3.948 0 1.808-1.07 3.473-2.76 4.163zM7.802 12.703l-1.95-1.142c-.167-.095-.239-.238-.239-.428V5.899c0-2.545 1.95-4.472 4.591-4.472 1 0 1.927.333 2.712.928L8.23 5.067c-.285.166-.428.404-.428.737v6.898zM12 15.128l-2.795-1.57v-3.33L12 8.658l2.795 1.57v3.33L12 15.128zm1.796 7.23c-1 0-1.927-.332-2.712-.927l4.686-2.712c.285-.166.428-.404.428-.737v-6.898l1.974 1.142c.167.095.238.238.238.428v5.233c0 2.545-1.974 4.472-4.614 4.472zm-5.637-5.303l-4.544-2.617c-1.308-.761-2.188-2.378-2.188-3.948A4.482 4.482 0 014.21 6.327v5.423c0 .333.143.571.428.738l5.947 3.449-1.95 1.118a.432.432 0 01-.476 0zm-.262 3.9c-2.688 0-4.662-2.021-4.662-4.519 0-.19.024-.38.047-.57l4.686 2.71c.286.167.571.167.856 0l5.97-3.448v2.26c0 .19-.07.333-.237.428l-4.543 2.616c-.619.357-1.356.523-2.117.523zm5.899 2.83a5.947 5.947 0 005.827-4.756C22.287 18.339 24 15.84 24 13.296c0-1.665-.713-3.282-1.998-4.448.119-.5.19-.999.19-1.498 0-3.401-2.759-5.947-5.946-5.947-.642 0-1.26.095-1.88.31A5.962 5.962 0 0010.205 0a5.947 5.947 0 00-5.827 4.757C1.713 5.447 0 7.945 0 10.49c0 1.666.713 3.283 1.998 4.448-.119.5-.19 1-.19 1.499 0 3.401 2.759 5.946 5.946 5.946.642 0 1.26-.095 1.88-.309a5.96 5.96 0 004.162 1.713z"></path></svg></span><span><b>GPT-6 Astra (max)</b><small>OpenAI</small></span></span><span class="num"><small>Score</small><b>0.790</b></span><span class="num"><small>Median cost</small>$14.25</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-astra-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-astra-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-astra-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-astra-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-astra-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gpt-6.1-sol-max.html"><span class="rk">5</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>OpenAI</title><path d="M9.205 8.658v-2.26c0-.19.072-.333.238-.428l4.543-2.616c.619-.357 1.356-.523 2.117-.523 2.854 0 4.662 2.212 4.662 4.566 0 .167 0 .357-.024.547l-4.71-2.759a.797.797 0 00-.856 0l-5.97 3.473zm10.609 8.8V12.06c0-.333-.143-.57-.429-.737l-5.97-3.473 1.95-1.118a.433.433 0 01.476 0l4.543 2.617c1.309.76 2.189 2.378 2.189 3.948 0 1.808-1.07 3.473-2.76 4.163zM7.802 12.703l-1.95-1.142c-.167-.095-.239-.238-.239-.428V5.899c0-2.545 1.95-4.472 4.591-4.472 1 0 1.927.333 2.712.928L8.23 5.067c-.285.166-.428.404-.428.737v6.898zM12 15.128l-2.795-1.57v-3.33L12 8.658l2.795 1.57v3.33L12 15.128zm1.796 7.23c-1 0-1.927-.332-2.712-.927l4.686-2.712c.285-.166.428-.404.428-.737v-6.898l1.974 1.142c.167.095.238.238.238.428v5.233c0 2.545-1.974 4.472-4.614 4.472zm-5.637-5.303l-4.544-2.617c-1.308-.761-2.188-2.378-2.188-3.948A4.482 4.482 0 014.21 6.327v5.423c0 .333.143.571.428.738l5.947 3.449-1.95 1.118a.432.432 0 01-.476 0zm-.262 3.9c-2.688 0-4.662-2.021-4.662-4.519 0-.19.024-.38.047-.57l4.686 2.71c.286.167.571.167.856 0l5.97-3.448v2.26c0 .19-.07.333-.237.428l-4.543 2.616c-.619.357-1.356.523-2.117.523zm5.899 2.83a5.947 5.947 0 005.827-4.756C22.287 18.339 24 15.84 24 13.296c0-1.665-.713-3.282-1.998-4.448.119-.5.19-.999.19-1.498 0-3.401-2.759-5.947-5.946-5.947-.642 0-1.26.095-1.88.31A5.962 5.962 0 0010.205 0a5.947 5.947 0 00-5.827 4.757C1.713 5.447 0 7.945 0 10.49c0 1.666.713 3.283 1.998 4.448-.119.5-.19 1-.19 1.499 0 3.401 2.759 5.946 5.946 5.946.642 0 1.26-.095 1.88-.309a5.96 5.96 0 004.162 1.713z"></path></svg></span><span><b>GPT-6.1 Sol (max)</b><small>OpenAI</small></span></span><span class="num"><small>Score</small><b>0.784</b></span><span class="num"><small>Median cost</small>$2.59</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6.1-sol-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6.1-sol-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6.1-sol-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6.1-sol-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6.1-sol-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gemini-4-argon-high.html"><span class="rk">6</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="url(#c4sGemG5)" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><defs><linearGradient id="c4sGemG5" x1="0" y1="0" x2="1" y2="1"><stop offset="0" stop-color="#4796E3"/><stop offset=".55" stop-color="#9168C0"/><stop offset="1" stop-color="#D96570"/></linearGradient></defs><title>Gemini</title><path d="M20.616 10.835a14.147 14.147 0 01-4.45-3.001 14.111 14.111 0 01-3.678-6.452.503.503 0 00-.975 0 14.134 14.134 0 01-3.679 6.452 14.155 14.155 0 01-4.45 3.001c-.65.28-1.318.505-2.002.678a.502.502 0 000 .975c.684.172 1.35.397 2.002.677a14.147 14.147 0 014.45 3.001 14.112 14.112 0 013.679 6.453.502.502 0 00.975 0c.172-.685.397-1.351.677-2.003a14.145 14.145 0 013.001-4.45 14.113 14.113 0 016.453-3.678.503.503 0 000-.975 13.245 13.245 0 01-2.003-.678z"></path></svg></span><span><b>Gemini 4 Argon (high)</b><small>Google</small></span></span><span class="num"><small>Score</small><b>0.777</b></span><span class="num"><small>Median cost</small>$4.83</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-4-argon-high/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-4-argon-high/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-4-argon-high/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-4-argon-high/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-4-argon-high/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gpt-5.6-sol-max.html"><span class="rk">7</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>OpenAI</title><path d="M9.205 8.658v-2.26c0-.19.072-.333.238-.428l4.543-2.616c.619-.357 1.356-.523 2.117-.523 2.854 0 4.662 2.212 4.662 4.566 0 .167 0 .357-.024.547l-4.71-2.759a.797.797 0 00-.856 0l-5.97 3.473zm10.609 8.8V12.06c0-.333-.143-.57-.429-.737l-5.97-3.473 1.95-1.118a.433.433 0 01.476 0l4.543 2.617c1.309.76 2.189 2.378 2.189 3.948 0 1.808-1.07 3.473-2.76 4.163zM7.802 12.703l-1.95-1.142c-.167-.095-.239-.238-.239-.428V5.899c0-2.545 1.95-4.472 4.591-4.472 1 0 1.927.333 2.712.928L8.23 5.067c-.285.166-.428.404-.428.737v6.898zM12 15.128l-2.795-1.57v-3.33L12 8.658l2.795 1.57v3.33L12 15.128zm1.796 7.23c-1 0-1.927-.332-2.712-.927l4.686-2.712c.285-.166.428-.404.428-.737v-6.898l1.974 1.142c.167.095.238.238.238.428v5.233c0 2.545-1.974 4.472-4.614 4.472zm-5.637-5.303l-4.544-2.617c-1.308-.761-2.188-2.378-2.188-3.948A4.482 4.482 0 014.21 6.327v5.423c0 .333.143.571.428.738l5.947 3.449-1.95 1.118a.432.432 0 01-.476 0zm-.262 3.9c-2.688 0-4.662-2.021-4.662-4.519 0-.19.024-.38.047-.57l4.686 2.71c.286.167.571.167.856 0l5.97-3.448v2.26c0 .19-.07.333-.237.428l-4.543 2.616c-.619.357-1.356.523-2.117.523zm5.899 2.83a5.947 5.947 0 005.827-4.756C22.287 18.339 24 15.84 24 13.296c0-1.665-.713-3.282-1.998-4.448.119-.5.19-.999.19-1.498 0-3.401-2.759-5.947-5.946-5.947-.642 0-1.26.095-1.88.31A5.962 5.962 0 0010.205 0a5.947 5.947 0 00-5.827 4.757C1.713 5.447 0 7.945 0 10.49c0 1.666.713 3.283 1.998 4.448-.119.5-.19 1-.19 1.499 0 3.401 2.759 5.946 5.946 5.946.642 0 1.26-.095 1.88-.309a5.96 5.96 0 004.162 1.713z"></path></svg></span><span><b>GPT-5.6 Sol (max)</b><small>OpenAI</small></span></span><span class="num"><small>Score</small><b>0.723</b></span><span class="num"><small>Median cost</small>$6.87</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-5.6-sol-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-5.6-sol-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-5.6-sol-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-5.6-sol-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-5.6-sol-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/claude-haiku-5.5-max.html"><span class="rk">8</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#D97757" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Claude</title><path d="M4.709 15.955l4.72-2.647.08-.23-.08-.128H9.2l-.79-.048-2.698-.073-2.339-.097-2.266-.122-.571-.121L0 11.784l.055-.352.48-.321.686.06 1.52.103 2.278.158 1.652.097 2.449.255h.389l.055-.157-.134-.098-.103-.097-2.358-1.596-2.552-1.688-1.336-.972-.724-.491-.364-.462-.158-1.008.656-.722.881.06.225.061.893.686 1.908 1.476 2.491 1.833.365.304.145-.103.019-.073-.164-.274-1.355-2.446-1.446-2.49-.644-1.032-.17-.619a2.97 2.97 0 01-.104-.729L6.283.134 6.696 0l.996.134.42.364.62 1.414 1.002 2.229 1.555 3.03.456.898.243.832.091.255h.158V9.01l.128-1.706.237-2.095.23-2.695.08-.76.376-.91.747-.492.584.28.48.685-.067.444-.286 1.851-.559 2.903-.364 1.942h.212l.243-.242.985-1.306 1.652-2.064.73-.82.85-.904.547-.431h1.033l.76 1.129-.34 1.166-1.064 1.347-.881 1.142-1.264 1.7-.79 1.36.073.11.188-.02 2.856-.606 1.543-.28 1.841-.315.833.388.091.395-.328.807-1.969.486-2.309.462-3.439.813-.042.03.049.061 1.549.146.662.036h1.622l3.02.225.79.522.474.638-.079.485-1.215.62-1.64-.389-3.829-.91-1.312-.329h-.182v.11l1.093 1.068 2.006 1.81 2.509 2.33.127.578-.322.455-.34-.049-2.205-1.657-.851-.747-1.926-1.62h-.128v.17l.444.649 2.345 3.521.122 1.08-.17.353-.608.213-.668-.122-1.374-1.925-1.415-2.167-1.143-1.943-.14.08-.674 7.254-.316.37-.729.28-.607-.461-.322-.747.322-1.476.389-1.924.315-1.53.286-1.9.17-.632-.012-.042-.14.018-1.434 1.967-2.18 2.945-1.726 1.845-.414.164-.717-.37.067-.662.401-.589 2.388-3.036 1.44-1.882.93-1.086-.006-.158h-.055L4.132 18.56l-1.13.146-.487-.456.061-.746.231-.243 1.908-1.312-.006.006z"></path></svg></span><span><b>Claude Haiku 5.5 (max)</b><small>Anthropic</small></span></span><span class="num"><small>Score</small><b>0.718</b></span><span class="num"><small>Median cost</small>$2.43</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-haiku-5.5-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-haiku-5.5-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-haiku-5.5-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-haiku-5.5-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-haiku-5.5-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/muse-wonder-full-1.0-max.html"><span class="rk">9</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#0081FB" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Meta</title><path d="M6.897 4c1.915 0 3.516.932 5.43 3.376l.282-.373c.19-.246.383-.484.58-.71l.313-.35C14.588 4.788 15.792 4 17.225 4c1.273 0 2.469.557 3.491 1.516l.218.213c1.73 1.765 2.917 4.71 3.053 8.026l.011.392.002.25c0 1.501-.28 2.759-.818 3.7l-.14.23-.108.153c-.301.42-.664.758-1.086 1.009l-.265.142-.087.04a3.493 3.493 0 01-.302.118 4.117 4.117 0 01-1.33.208c-.524 0-.996-.067-1.438-.215-.614-.204-1.163-.56-1.726-1.116l-.227-.235c-.753-.812-1.534-1.976-2.493-3.586l-1.43-2.41-.544-.895-1.766 3.13-.343.592C7.597 19.156 6.227 20 4.356 20c-1.21 0-2.205-.42-2.936-1.182l-.168-.184c-.484-.573-.837-1.311-1.043-2.189l-.067-.32a8.69 8.69 0 01-.136-1.288L0 14.468c.002-.745.06-1.49.174-2.23l.1-.573c.298-1.53.828-2.958 1.536-4.157l.209-.34c1.177-1.83 2.789-3.053 4.615-3.16L6.897 4zm-.033 2.615l-.201.01c-.83.083-1.606.673-2.252 1.577l-.138.199-.01.018c-.67 1.017-1.185 2.378-1.456 3.845l-.004.022a12.591 12.591 0 00-.207 2.254l.002.188c.004.18.017.36.04.54l.043.291c.092.503.257.908.486 1.208l.117.137c.303.323.698.492 1.17.492 1.1 0 1.796-.676 3.696-3.641l2.175-3.4.454-.701-.139-.198C9.11 7.3 8.084 6.616 6.864 6.616zm10.196-.552l-.176.007c-.635.048-1.223.359-1.82.933l-.196.198c-.439.462-.887 1.064-1.367 1.807l.266.398c.18.274.362.56.55.858l.293.475 1.396 2.335.695 1.114c.583.926 1.03 1.6 1.408 2.082l.213.262c.282.326.529.54.777.673l.102.05c.227.1.457.138.718.138.176.002.35-.023.518-.073.338-.104.61-.32.813-.637l.095-.163.077-.162c.194-.459.29-1.06.29-1.785l-.006-.449c-.08-2.871-.938-5.372-2.2-6.798l-.176-.189c-.67-.683-1.444-1.074-2.27-1.074z"></path></svg></span><span><b>Muse Wonder Full 1.0 (max)</b><small>Meta</small></span></span><span class="num"><small>Score</small><b>0.715</b></span><span class="num" title="Muse Wonder Full 1.0 (max): sold by subscription; cost = the token counts its CLI logs, at Muse Wonder&#x27;s per-token list price"><small>Median cost</small>$3.66*</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-wonder-full-1.0-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-wonder-full-1.0-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-wonder-full-1.0-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-wonder-full-1.0-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-wonder-full-1.0-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gemini-3.8-flash-high.html"><span class="rk">10</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="url(#c4sGemG9)" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><defs><linearGradient id="c4sGemG9" x1="0" y1="0" x2="1" y2="1"><stop offset="0" stop-color="#4796E3"/><stop offset=".55" stop-color="#9168C0"/><stop offset="1" stop-color="#D96570"/></linearGradient></defs><title>Gemini</title><path d="M20.616 10.835a14.147 14.147 0 01-4.45-3.001 14.111 14.111 0 01-3.678-6.452.503.503 0 00-.975 0 14.134 14.134 0 01-3.679 6.452 14.155 14.155 0 01-4.45 3.001c-.65.28-1.318.505-2.002.678a.502.502 0 000 .975c.684.172 1.35.397 2.002.677a14.147 14.147 0 014.45 3.001 14.112 14.112 0 013.679 6.453.502.502 0 00.975 0c.172-.685.397-1.351.677-2.003a14.145 14.145 0 013.001-4.45 14.113 14.113 0 016.453-3.678.503.503 0 000-.975 13.245 13.245 0 01-2.003-.678z"></path></svg></span><span><b>Gemini 3.8 Flash (high)</b><small>Google</small></span></span><span class="num"><small>Score</small><b>0.694</b></span><span class="num"><small>Median cost</small>$3.85</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-3.8-flash-high/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-3.8-flash-high/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-3.8-flash-high/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-3.8-flash-high/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-3.8-flash-high/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gpt-6-luna-max.html"><span class="rk">11</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>OpenAI</title><path d="M9.205 8.658v-2.26c0-.19.072-.333.238-.428l4.543-2.616c.619-.357 1.356-.523 2.117-.523 2.854 0 4.662 2.212 4.662 4.566 0 .167 0 .357-.024.547l-4.71-2.759a.797.797 0 00-.856 0l-5.97 3.473zm10.609 8.8V12.06c0-.333-.143-.57-.429-.737l-5.97-3.473 1.95-1.118a.433.433 0 01.476 0l4.543 2.617c1.309.76 2.189 2.378 2.189 3.948 0 1.808-1.07 3.473-2.76 4.163zM7.802 12.703l-1.95-1.142c-.167-.095-.239-.238-.239-.428V5.899c0-2.545 1.95-4.472 4.591-4.472 1 0 1.927.333 2.712.928L8.23 5.067c-.285.166-.428.404-.428.737v6.898zM12 15.128l-2.795-1.57v-3.33L12 8.658l2.795 1.57v3.33L12 15.128zm1.796 7.23c-1 0-1.927-.332-2.712-.927l4.686-2.712c.285-.166.428-.404.428-.737v-6.898l1.974 1.142c.167.095.238.238.238.428v5.233c0 2.545-1.974 4.472-4.614 4.472zm-5.637-5.303l-4.544-2.617c-1.308-.761-2.188-2.378-2.188-3.948A4.482 4.482 0 014.21 6.327v5.423c0 .333.143.571.428.738l5.947 3.449-1.95 1.118a.432.432 0 01-.476 0zm-.262 3.9c-2.688 0-4.662-2.021-4.662-4.519 0-.19.024-.38.047-.57l4.686 2.71c.286.167.571.167.856 0l5.97-3.448v2.26c0 .19-.07.333-.237.428l-4.543 2.616c-.619.357-1.356.523-2.117.523zm5.899 2.83a5.947 5.947 0 005.827-4.756C22.287 18.339 24 15.84 24 13.296c0-1.665-.713-3.282-1.998-4.448.119-.5.19-.999.19-1.498 0-3.401-2.759-5.947-5.946-5.947-.642 0-1.26.095-1.88.31A5.962 5.962 0 0010.205 0a5.947 5.947 0 00-5.827 4.757C1.713 5.447 0 7.945 0 10.49c0 1.666.713 3.283 1.998 4.448-.119.5-.19 1-.19 1.499 0 3.401 2.759 5.946 5.946 5.946.642 0 1.26-.095 1.88-.309a5.96 5.96 0 004.162 1.713z"></path></svg></span><span><b>GPT-6 Luna (max)</b><small>OpenAI</small></span></span><span class="num"><small>Score</small><b>0.688</b></span><span class="num"><small>Median cost</small>$0.16</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-luna-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-luna-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-luna-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-luna-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-luna-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/grok-4.6-xhigh.html"><span class="rk">12</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Grok</title><path d="M9.27 15.29l7.978-5.897c.391-.29.95-.177 1.137.272.98 2.369.542 5.215-1.41 7.169-1.951 1.954-4.667 2.382-7.149 1.406l-2.711 1.257c3.889 2.661 8.611 2.003 11.562-.953 2.341-2.344 3.066-5.539 2.388-8.42l.006.007c-.983-4.232.242-5.924 2.75-9.383.06-.082.12-.164.179-.248l-3.301 3.305v-.01L9.267 15.292M7.623 16.723c-2.792-2.67-2.31-6.801.071-9.184 1.761-1.763 4.647-2.483 7.166-1.425l2.705-1.25a7.808 7.808 0 00-1.829-1A8.975 8.975 0 005.984 5.83c-2.533 2.536-3.33 6.436-1.962 9.764 1.022 2.487-.653 4.246-2.34 6.022-.599.63-1.199 1.259-1.682 1.925l7.62-6.815"></path></svg></span><span><b>Grok 4.6 (xhigh)</b><small>xAI</small></span></span><span class="num"><small>Score</small><b>0.625</b></span><span class="num"><small>Median cost</small>$7.41</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.6-xhigh/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.6-xhigh/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.6-xhigh/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.6-xhigh/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.6-xhigh/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/muse-spark-open-max.html"><span class="rk">13</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#0081FB" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Meta</title><path d="M6.897 4c1.915 0 3.516.932 5.43 3.376l.282-.373c.19-.246.383-.484.58-.71l.313-.35C14.588 4.788 15.792 4 17.225 4c1.273 0 2.469.557 3.491 1.516l.218.213c1.73 1.765 2.917 4.71 3.053 8.026l.011.392.002.25c0 1.501-.28 2.759-.818 3.7l-.14.23-.108.153c-.301.42-.664.758-1.086 1.009l-.265.142-.087.04a3.493 3.493 0 01-.302.118 4.117 4.117 0 01-1.33.208c-.524 0-.996-.067-1.438-.215-.614-.204-1.163-.56-1.726-1.116l-.227-.235c-.753-.812-1.534-1.976-2.493-3.586l-1.43-2.41-.544-.895-1.766 3.13-.343.592C7.597 19.156 6.227 20 4.356 20c-1.21 0-2.205-.42-2.936-1.182l-.168-.184c-.484-.573-.837-1.311-1.043-2.189l-.067-.32a8.69 8.69 0 01-.136-1.288L0 14.468c.002-.745.06-1.49.174-2.23l.1-.573c.298-1.53.828-2.958 1.536-4.157l.209-.34c1.177-1.83 2.789-3.053 4.615-3.16L6.897 4zm-.033 2.615l-.201.01c-.83.083-1.606.673-2.252 1.577l-.138.199-.01.018c-.67 1.017-1.185 2.378-1.456 3.845l-.004.022a12.591 12.591 0 00-.207 2.254l.002.188c.004.18.017.36.04.54l.043.291c.092.503.257.908.486 1.208l.117.137c.303.323.698.492 1.17.492 1.1 0 1.796-.676 3.696-3.641l2.175-3.4.454-.701-.139-.198C9.11 7.3 8.084 6.616 6.864 6.616zm10.196-.552l-.176.007c-.635.048-1.223.359-1.82.933l-.196.198c-.439.462-.887 1.064-1.367 1.807l.266.398c.18.274.362.56.55.858l.293.475 1.396 2.335.695 1.114c.583.926 1.03 1.6 1.408 2.082l.213.262c.282.326.529.54.777.673l.102.05c.227.1.457.138.718.138.176.002.35-.023.518-.073.338-.104.61-.32.813-.637l.095-.163.077-.162c.194-.459.29-1.06.29-1.785l-.006-.449c-.08-2.871-.938-5.372-2.2-6.798l-.176-.189c-.67-.683-1.444-1.074-2.27-1.074z"></path></svg></span><span><b>Muse Spark Open (max)</b><small>Meta</small></span></span><span class="num"><small>Score</small><b>0.611</b></span><span class="num"><small>Median cost</small>$2.01</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-open-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-open-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-open-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-open-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-open-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/muse-spark-1.3-max.html"><span class="rk">14</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#0081FB" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Meta</title><path d="M6.897 4c1.915 0 3.516.932 5.43 3.376l.282-.373c.19-.246.383-.484.58-.71l.313-.35C14.588 4.788 15.792 4 17.225 4c1.273 0 2.469.557 3.491 1.516l.218.213c1.73 1.765 2.917 4.71 3.053 8.026l.011.392.002.25c0 1.501-.28 2.759-.818 3.7l-.14.23-.108.153c-.301.42-.664.758-1.086 1.009l-.265.142-.087.04a3.493 3.493 0 01-.302.118 4.117 4.117 0 01-1.33.208c-.524 0-.996-.067-1.438-.215-.614-.204-1.163-.56-1.726-1.116l-.227-.235c-.753-.812-1.534-1.976-2.493-3.586l-1.43-2.41-.544-.895-1.766 3.13-.343.592C7.597 19.156 6.227 20 4.356 20c-1.21 0-2.205-.42-2.936-1.182l-.168-.184c-.484-.573-.837-1.311-1.043-2.189l-.067-.32a8.69 8.69 0 01-.136-1.288L0 14.468c.002-.745.06-1.49.174-2.23l.1-.573c.298-1.53.828-2.958 1.536-4.157l.209-.34c1.177-1.83 2.789-3.053 4.615-3.16L6.897 4zm-.033 2.615l-.201.01c-.83.083-1.606.673-2.252 1.577l-.138.199-.01.018c-.67 1.017-1.185 2.378-1.456 3.845l-.004.022a12.591 12.591 0 00-.207 2.254l.002.188c.004.18.017.36.04.54l.043.291c.092.503.257.908.486 1.208l.117.137c.303.323.698.492 1.17.492 1.1 0 1.796-.676 3.696-3.641l2.175-3.4.454-.701-.139-.198C9.11 7.3 8.084 6.616 6.864 6.616zm10.196-.552l-.176.007c-.635.048-1.223.359-1.82.933l-.196.198c-.439.462-.887 1.064-1.367 1.807l.266.398c.18.274.362.56.55.858l.293.475 1.396 2.335.695 1.114c.583.926 1.03 1.6 1.408 2.082l.213.262c.282.326.529.54.777.673l.102.05c.227.1.457.138.718.138.176.002.35-.023.518-.073.338-.104.61-.32.813-.637l.095-.163.077-.162c.194-.459.29-1.06.29-1.785l-.006-.449c-.08-2.871-.938-5.372-2.2-6.798l-.176-.189c-.67-.683-1.444-1.074-2.27-1.074z"></path></svg></span><span><b>Muse Spark 1.3 (max)</b><small>Meta</small></span></span><span class="num"><small>Score</small><b>0.548</b></span><span class="num"><small>Median cost</small>$0.23</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-1.3-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-1.3-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-1.3-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-1.3-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-1.3-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/glm-5.3-flash-max.html"><span class="rk">15</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Z.ai</title><path d="M12.105 2L9.927 4.953H.653L2.83 2h9.276zM23.254 19.048L21.078 22h-9.242l2.174-2.952h9.244zM24 2L9.264 22H0L14.736 2H24z"></path></svg></span><span><b>GLM-5.3 Flash (max)</b><small>Z.ai</small></span></span><span class="num"><small>Score</small><b>0.542</b></span><span class="num"><small>Median cost</small>$0.94</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/glm-5.3-flash-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/glm-5.3-flash-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/glm-5.3-flash-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/glm-5.3-flash-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/glm-5.3-flash-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/grok-4.7-xhigh.html"><span class="rk">16</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Grok</title><path d="M9.27 15.29l7.978-5.897c.391-.29.95-.177 1.137.272.98 2.369.542 5.215-1.41 7.169-1.951 1.954-4.667 2.382-7.149 1.406l-2.711 1.257c3.889 2.661 8.611 2.003 11.562-.953 2.341-2.344 3.066-5.539 2.388-8.42l.006.007c-.983-4.232.242-5.924 2.75-9.383.06-.082.12-.164.179-.248l-3.301 3.305v-.01L9.267 15.292M7.623 16.723c-2.792-2.67-2.31-6.801.071-9.184 1.761-1.763 4.647-2.483 7.166-1.425l2.705-1.25a7.808 7.808 0 00-1.829-1A8.975 8.975 0 005.984 5.83c-2.533 2.536-3.33 6.436-1.962 9.764 1.022 2.487-.653 4.246-2.34 6.022-.599.63-1.199 1.259-1.682 1.925l7.62-6.815"></path></svg></span><span><b>Grok 4.7 (xhigh)</b><small>xAI</small></span></span><span class="num"><small>Score</small><b>0.541</b></span><span class="num"><small>Median cost</small>$7.29</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.7-xhigh/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.7-xhigh/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.7-xhigh/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.7-xhigh/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.7-xhigh/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/mimo-v2.6-pro-max.html"><span class="rk">17</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#FF6900" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Xiaomi</title><path d="M12 0C8.016 0 4.756.255 2.493 2.516.23 4.776 0 8.033 0 12.012c0 3.98.23 7.235 2.494 9.497C4.757 23.77 8.017 24 12 24c3.983 0 7.243-.23 9.506-2.491C23.77 19.247 24 15.99 24 12.012c0-3.984-.233-7.243-2.502-9.504C19.234.252 15.978 0 12 0zM4.906 7.405h5.624c1.47 0 3.007.068 3.764.827.746.746.827 2.233.83 3.676v4.54a.15.15 0 0 1-.152.147h-1.947a.15.15 0 0 1-.152-.148V11.83c-.002-.806-.048-1.634-.464-2.051-.358-.36-1.026-.441-1.72-.458H7.158a.15.15 0 0 0-.151.147v6.98a.15.15 0 0 1-.152.148H4.906a.15.15 0 0 1-.15-.148V7.554a.15.15 0 0 1 .15-.149zm12.131 0h1.949a.15.15 0 0 1 .15.15v8.892a.15.15 0 0 1-.15.148h-1.949a.15.15 0 0 1-.151-.148V7.554a.15.15 0 0 1 .151-.149zM8.92 10.948h2.046c.083 0 .15.066.15.147v5.352a.15.15 0 0 1-.15.148H8.92a.15.15 0 0 1-.152-.148v-5.352a.15.15 0 0 1 .152-.147Z"/></svg></span><span><b>MiMo V2.6 Pro (max)</b><small>Xiaomi</small></span></span><span class="num"><small>Score</small><b>0.527</b></span><span class="num"><small>Median cost</small>$0.92</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/mimo-v2.6-pro-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/mimo-v2.6-pro-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/mimo-v2.6-pro-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/mimo-v2.6-pro-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/mimo-v2.6-pro-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gemma-4-31b-thinking-on.html"><span class="rk">18</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="url(#c4sGemG17)" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><defs><linearGradient id="c4sGemG17" x1="0" y1="0" x2="1" y2="1"><stop offset="0" stop-color="#4796E3"/><stop offset=".55" stop-color="#9168C0"/><stop offset="1" stop-color="#D96570"/></linearGradient></defs><title>Gemini</title><path d="M20.616 10.835a14.147 14.147 0 01-4.45-3.001 14.111 14.111 0 01-3.678-6.452.503.503 0 00-.975 0 14.134 14.134 0 01-3.679 6.452 14.155 14.155 0 01-4.45 3.001c-.65.28-1.318.505-2.002.678a.502.502 0 000 .975c.684.172 1.35.397 2.002.677a14.147 14.147 0 014.45 3.001 14.112 14.112 0 013.679 6.453.502.502 0 00.975 0c.172-.685.397-1.351.677-2.003a14.145 14.145 0 013.001-4.45 14.113 14.113 0 016.453-3.678.503.503 0 000-.975 13.245 13.245 0 01-2.003-.678z"></path></svg></span><span><b>Gemma 4 31B (thinking on)</b><small>Google</small></span></span><span class="num"><small>Score</small><b>0.517</b></span><span class="num" title="Gemma 4 31B (thinking on): it ran on self-hosted weights, so nothing was billed"><small>Median cost</small>–</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gemma-4-31b-thinking-on/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemma-4-31b-thinking-on/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemma-4-31b-thinking-on/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemma-4-31b-thinking-on/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemma-4-31b-thinking-on/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/deepseek-v4.1-flash-max.html"><span class="rk">19</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#4D6BFE" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>DeepSeek</title><path d="M23.748 4.482c-.254-.124-.364.113-.512.234-.051.039-.094.09-.137.136-.372.397-.806.657-1.373.626-.829-.046-1.537.214-2.163.848-.133-.782-.575-1.248-1.247-1.548-.352-.156-.708-.311-.955-.65-.172-.241-.219-.51-.305-.774-.055-.16-.11-.323-.293-.35-.2-.031-.278.136-.356.276-.313.572-.434 1.202-.422 1.84.027 1.436.633 2.58 1.838 3.393.137.093.172.187.129.323-.082.28-.18.552-.266.833-.055.179-.137.217-.329.14a5.526 5.526 0 01-1.736-1.18c-.857-.828-1.631-1.742-2.597-2.458a11.365 11.365 0 00-.689-.471c-.985-.957.13-1.743.388-1.836.27-.098.093-.432-.779-.428-.872.004-1.67.295-2.687.684a3.055 3.055 0 01-.465.137 9.597 9.597 0 00-2.883-.102c-1.885.21-3.39 1.102-4.497 2.623C.082 8.606-.231 10.684.152 12.85c.403 2.284 1.569 4.175 3.36 5.653 1.858 1.533 3.997 2.284 6.438 2.14 1.482-.085 3.133-.284 4.994-1.86.47.234.962.327 1.78.397.63.059 1.236-.03 1.705-.128.735-.156.684-.837.419-.961-2.155-1.004-1.682-.595-2.113-.926 1.096-1.296 2.746-2.642 3.392-7.003.05-.347.007-.565 0-.845-.004-.17.035-.237.23-.256a4.173 4.173 0 001.545-.475c1.396-.763 1.96-2.015 2.093-3.517.02-.23-.004-.467-.247-.588zM11.581 18c-2.089-1.642-3.102-2.183-3.52-2.16-.392.024-.321.471-.235.763.09.288.207.486.371.739.114.167.192.416-.113.603-.673.416-1.842-.14-1.897-.167-1.361-.802-2.5-1.86-3.301-3.307-.774-1.393-1.224-2.887-1.298-4.482-.02-.386.093-.522.477-.592a4.696 4.696 0 011.529-.039c2.132.312 3.946 1.265 5.468 2.774.868.86 1.525 1.887 2.202 2.891.72 1.066 1.494 2.082 2.48 2.914.348.292.625.514.891.677-.802.09-2.14.11-3.054-.614zm1-6.44a.306.306 0 01.415-.287.302.302 0 01.2.288.306.306 0 01-.31.307.303.303 0 01-.304-.308zm3.11 1.596c-.2.081-.399.151-.59.16a1.245 1.245 0 01-.798-.254c-.274-.23-.47-.358-.552-.758a1.73 1.73 0 01.016-.588c.07-.327-.008-.537-.239-.727-.187-.156-.426-.199-.688-.199a.559.559 0 01-.254-.078c-.11-.054-.2-.19-.114-.358.028-.054.16-.186.192-.21.356-.202.767-.136 1.146.016.352.144.618.408 1.001.782.391.451.462.576.685.914.176.265.336.537.445.848.067.195-.019.354-.25.452z"></path></svg></span><span><b>DeepSeek V4.1 Flash (max)</b><small>DeepSeek</small></span></span><span class="num"><small>Score</small><b>0.366</b></span><span class="num"><small>Median cost</small>$0.35</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/deepseek-v4.1-flash-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/deepseek-v4.1-flash-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/deepseek-v4.1-flash-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/deepseek-v4.1-flash-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/deepseek-v4.1-flash-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li></ol></div></section>
 </main>
 <footer><p>Code4Scene  ·  UC San Diego &amp; UC Berkeley  ·  <a href="https://arxiv.org/abs/2609.36777" rel="noopener" target="_blank">arXiv:2609.36777</a>  ·  <a href="https://github.com/SimWorld-AI/Code4Scene" rel="noopener" target="_blank">GitHub</a>  ·  <a href="https://simworld.org/" rel="noopener" target="_blank">SimWorld Home</a></p></footer>
 <script defer src="../assets/gallery.js?v=20261016t2s"></script>

 </head><body class="gallery-page"><a class="skip-link" href="#main">Skip to the gallery</a>
 <header class="site-header"><div class="brand"><a aria-label="Code4Scene home" class="brand-home" href="../index.html#top"><svg aria-hidden="true" fill="none" viewbox="0 0 30 32"><path d="M15 2 27 9v14l-12 7L3 23V9L15 2Z M3 9l12 7 12-7 M15 16v14 M9 5.5l12 7v14 M21 5.5l-12 7v14" stroke="currentColor" stroke-linejoin="round" stroke-width="1.6"></path></svg><span>Code4Scene</span></a><a class="brand-by" href="https://simworld.org/">by SimWorld</a></div><nav aria-label="Main navigation"><a href="../index.html#top">Benchmark</a><a href="../index.html#leaderboard">Leaderboard</a><a href="../index.html#cases">Visualization</a><a class="nav-active" href="../gallery/index.html">Gallery</a><a href="https://arxiv.org/abs/2609.36777" rel="noopener" target="_blank">Paper ↗</a><a href="https://github.com/SimWorld-AI/Code4Scene" rel="noopener" target="_blank">Github ↗</a></nav></header>
 <main class="page-main" id="main">
+<section class="gal-top"><div class="container"><span class="section-label">Gallery</span><h1 class="section-title">Every scene, every agent</h1><p class="section-desc">What each configuration built on the 20 Research Track scenes in the October 2026 Text-to-Scene re-run, as the evaluator saw it: four renders per scene from the benchmark&#x27;s own cameras, with the case score and the agent&#x27;s cost. Scores are truncated to three decimals; a case without a valid scene scores 0.</p><nav aria-label="Browse the gallery" class="gal-switch"><a aria-current="page" class="on" href="index.html">By agent</a><a href="cases.html">By scene</a></nav></div></section><section class="gal-body"><div class="container"><p class="gal-note">In leaderboard order. The strip shows the same five scenes for every agent: Blue City, Cyberpunk, Egyptian Temple, Nordic Harbour, Winter Town.</p><ol class="gal-agents"><li><a class="gal-agent" href="model/claude-sonnet-5.5-max.html"><span class="rk">1</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#D97757" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Claude</title><path d="M4.709 15.955l4.72-2.647.08-.23-.08-.128H9.2l-.79-.048-2.698-.073-2.339-.097-2.266-.122-.571-.121L0 11.784l.055-.352.48-.321.686.06 1.52.103 2.278.158 1.652.097 2.449.255h.389l.055-.157-.134-.098-.103-.097-2.358-1.596-2.552-1.688-1.336-.972-.724-.491-.364-.462-.158-1.008.656-.722.881.06.225.061.893.686 1.908 1.476 2.491 1.833.365.304.145-.103.019-.073-.164-.274-1.355-2.446-1.446-2.49-.644-1.032-.17-.619a2.97 2.97 0 01-.104-.729L6.283.134 6.696 0l.996.134.42.364.62 1.414 1.002 2.229 1.555 3.03.456.898.243.832.091.255h.158V9.01l.128-1.706.237-2.095.23-2.695.08-.76.376-.91.747-.492.584.28.48.685-.067.444-.286 1.851-.559 2.903-.364 1.942h.212l.243-.242.985-1.306 1.652-2.064.73-.82.85-.904.547-.431h1.033l.76 1.129-.34 1.166-1.064 1.347-.881 1.142-1.264 1.7-.79 1.36.073.11.188-.02 2.856-.606 1.543-.28 1.841-.315.833.388.091.395-.328.807-1.969.486-2.309.462-3.439.813-.042.03.049.061 1.549.146.662.036h1.622l3.02.225.79.522.474.638-.079.485-1.215.62-1.64-.389-3.829-.91-1.312-.329h-.182v.11l1.093 1.068 2.006 1.81 2.509 2.33.127.578-.322.455-.34-.049-2.205-1.657-.851-.747-1.926-1.62h-.128v.17l.444.649 2.345 3.521.122 1.08-.17.353-.608.213-.668-.122-1.374-1.925-1.415-2.167-1.143-1.943-.14.08-.674 7.254-.316.37-.729.28-.607-.461-.322-.747.322-1.476.389-1.924.315-1.53.286-1.9.17-.632-.012-.042-.14.018-1.434 1.967-2.18 2.945-1.726 1.845-.414.164-.717-.37.067-.662.401-.589 2.388-3.036 1.44-1.882.93-1.086-.006-.158h-.055L4.132 18.56l-1.13.146-.487-.456.061-.746.231-.243 1.908-1.312-.006.006z"></path></svg></span><span><b>Claude Sonnet 5.5 (max)</b><small>Anthropic</small></span></span><span class="num"><small>Score</small><b>0.837</b></span><span class="num"><small>Median cost</small>$26.93</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-sonnet-5.5-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-sonnet-5.5-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-sonnet-5.5-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-sonnet-5.5-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-sonnet-5.5-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/claude-opus-5.5-max.html"><span class="rk">2</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#D97757" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Claude</title><path d="M4.709 15.955l4.72-2.647.08-.23-.08-.128H9.2l-.79-.048-2.698-.073-2.339-.097-2.266-.122-.571-.121L0 11.784l.055-.352.48-.321.686.06 1.52.103 2.278.158 1.652.097 2.449.255h.389l.055-.157-.134-.098-.103-.097-2.358-1.596-2.552-1.688-1.336-.972-.724-.491-.364-.462-.158-1.008.656-.722.881.06.225.061.893.686 1.908 1.476 2.491 1.833.365.304.145-.103.019-.073-.164-.274-1.355-2.446-1.446-2.49-.644-1.032-.17-.619a2.97 2.97 0 01-.104-.729L6.283.134 6.696 0l.996.134.42.364.62 1.414 1.002 2.229 1.555 3.03.456.898.243.832.091.255h.158V9.01l.128-1.706.237-2.095.23-2.695.08-.76.376-.91.747-.492.584.28.48.685-.067.444-.286 1.851-.559 2.903-.364 1.942h.212l.243-.242.985-1.306 1.652-2.064.73-.82.85-.904.547-.431h1.033l.76 1.129-.34 1.166-1.064 1.347-.881 1.142-1.264 1.7-.79 1.36.073.11.188-.02 2.856-.606 1.543-.28 1.841-.315.833.388.091.395-.328.807-1.969.486-2.309.462-3.439.813-.042.03.049.061 1.549.146.662.036h1.622l3.02.225.79.522.474.638-.079.485-1.215.62-1.64-.389-3.829-.91-1.312-.329h-.182v.11l1.093 1.068 2.006 1.81 2.509 2.33.127.578-.322.455-.34-.049-2.205-1.657-.851-.747-1.926-1.62h-.128v.17l.444.649 2.345 3.521.122 1.08-.17.353-.608.213-.668-.122-1.374-1.925-1.415-2.167-1.143-1.943-.14.08-.674 7.254-.316.37-.729.28-.607-.461-.322-.747.322-1.476.389-1.924.315-1.53.286-1.9.17-.632-.012-.042-.14.018-1.434 1.967-2.18 2.945-1.726 1.845-.414.164-.717-.37.067-.662.401-.589 2.388-3.036 1.44-1.882.93-1.086-.006-.158h-.055L4.132 18.56l-1.13.146-.487-.456.061-.746.231-.243 1.908-1.312-.006.006z"></path></svg></span><span><b>Claude Opus 5.5 (max)</b><small>Anthropic</small></span></span><span class="num"><small>Score</small><b>0.832</b></span><span class="num"><small>Median cost</small>$26.90</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-opus-5.5-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-opus-5.5-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-opus-5.5-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-opus-5.5-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-opus-5.5-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/claude-fable-5.1-max.html"><span class="rk">3</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#D97757" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Claude</title><path d="M4.709 15.955l4.72-2.647.08-.23-.08-.128H9.2l-.79-.048-2.698-.073-2.339-.097-2.266-.122-.571-.121L0 11.784l.055-.352.48-.321.686.06 1.52.103 2.278.158 1.652.097 2.449.255h.389l.055-.157-.134-.098-.103-.097-2.358-1.596-2.552-1.688-1.336-.972-.724-.491-.364-.462-.158-1.008.656-.722.881.06.225.061.893.686 1.908 1.476 2.491 1.833.365.304.145-.103.019-.073-.164-.274-1.355-2.446-1.446-2.49-.644-1.032-.17-.619a2.97 2.97 0 01-.104-.729L6.283.134 6.696 0l.996.134.42.364.62 1.414 1.002 2.229 1.555 3.03.456.898.243.832.091.255h.158V9.01l.128-1.706.237-2.095.23-2.695.08-.76.376-.91.747-.492.584.28.48.685-.067.444-.286 1.851-.559 2.903-.364 1.942h.212l.243-.242.985-1.306 1.652-2.064.73-.82.85-.904.547-.431h1.033l.76 1.129-.34 1.166-1.064 1.347-.881 1.142-1.264 1.7-.79 1.36.073.11.188-.02 2.856-.606 1.543-.28 1.841-.315.833.388.091.395-.328.807-1.969.486-2.309.462-3.439.813-.042.03.049.061 1.549.146.662.036h1.622l3.02.225.79.522.474.638-.079.485-1.215.62-1.64-.389-3.829-.91-1.312-.329h-.182v.11l1.093 1.068 2.006 1.81 2.509 2.33.127.578-.322.455-.34-.049-2.205-1.657-.851-.747-1.926-1.62h-.128v.17l.444.649 2.345 3.521.122 1.08-.17.353-.608.213-.668-.122-1.374-1.925-1.415-2.167-1.143-1.943-.14.08-.674 7.254-.316.37-.729.28-.607-.461-.322-.747.322-1.476.389-1.924.315-1.53.286-1.9.17-.632-.012-.042-.14.018-1.434 1.967-2.18 2.945-1.726 1.845-.414.164-.717-.37.067-.662.401-.589 2.388-3.036 1.44-1.882.93-1.086-.006-.158h-.055L4.132 18.56l-1.13.146-.487-.456.061-.746.231-.243 1.908-1.312-.006.006z"></path></svg></span><span><b>Claude Fable 5.1 (max)</b><small>Anthropic</small></span></span><span class="num"><small>Score</small><b>0.800</b></span><span class="num"><small>Median cost</small>$23.42</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-fable-5.1-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-fable-5.1-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-fable-5.1-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-fable-5.1-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-fable-5.1-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gpt-6-astra-max.html"><span class="rk">4</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>OpenAI</title><path d="M9.205 8.658v-2.26c0-.19.072-.333.238-.428l4.543-2.616c.619-.357 1.356-.523 2.117-.523 2.854 0 4.662 2.212 4.662 4.566 0 .167 0 .357-.024.547l-4.71-2.759a.797.797 0 00-.856 0l-5.97 3.473zm10.609 8.8V12.06c0-.333-.143-.57-.429-.737l-5.97-3.473 1.95-1.118a.433.433 0 01.476 0l4.543 2.617c1.309.76 2.189 2.378 2.189 3.948 0 1.808-1.07 3.473-2.76 4.163zM7.802 12.703l-1.95-1.142c-.167-.095-.239-.238-.239-.428V5.899c0-2.545 1.95-4.472 4.591-4.472 1 0 1.927.333 2.712.928L8.23 5.067c-.285.166-.428.404-.428.737v6.898zM12 15.128l-2.795-1.57v-3.33L12 8.658l2.795 1.57v3.33L12 15.128zm1.796 7.23c-1 0-1.927-.332-2.712-.927l4.686-2.712c.285-.166.428-.404.428-.737v-6.898l1.974 1.142c.167.095.238.238.238.428v5.233c0 2.545-1.974 4.472-4.614 4.472zm-5.637-5.303l-4.544-2.617c-1.308-.761-2.188-2.378-2.188-3.948A4.482 4.482 0 014.21 6.327v5.423c0 .333.143.571.428.738l5.947 3.449-1.95 1.118a.432.432 0 01-.476 0zm-.262 3.9c-2.688 0-4.662-2.021-4.662-4.519 0-.19.024-.38.047-.57l4.686 2.71c.286.167.571.167.856 0l5.97-3.448v2.26c0 .19-.07.333-.237.428l-4.543 2.616c-.619.357-1.356.523-2.117.523zm5.899 2.83a5.947 5.947 0 005.827-4.756C22.287 18.339 24 15.84 24 13.296c0-1.665-.713-3.282-1.998-4.448.119-.5.19-.999.19-1.498 0-3.401-2.759-5.947-5.946-5.947-.642 0-1.26.095-1.88.31A5.962 5.962 0 0010.205 0a5.947 5.947 0 00-5.827 4.757C1.713 5.447 0 7.945 0 10.49c0 1.666.713 3.283 1.998 4.448-.119.5-.19 1-.19 1.499 0 3.401 2.759 5.946 5.946 5.946.642 0 1.26-.095 1.88-.309a5.96 5.96 0 004.162 1.713z"></path></svg></span><span><b>GPT-6 Astra (max)</b><small>OpenAI</small></span></span><span class="num"><small>Score</small><b>0.790</b></span><span class="num"><small>Median cost</small>$14.25</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-astra-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-astra-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-astra-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-astra-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-astra-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gpt-6.1-sol-max.html"><span class="rk">5</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>OpenAI</title><path d="M9.205 8.658v-2.26c0-.19.072-.333.238-.428l4.543-2.616c.619-.357 1.356-.523 2.117-.523 2.854 0 4.662 2.212 4.662 4.566 0 .167 0 .357-.024.547l-4.71-2.759a.797.797 0 00-.856 0l-5.97 3.473zm10.609 8.8V12.06c0-.333-.143-.57-.429-.737l-5.97-3.473 1.95-1.118a.433.433 0 01.476 0l4.543 2.617c1.309.76 2.189 2.378 2.189 3.948 0 1.808-1.07 3.473-2.76 4.163zM7.802 12.703l-1.95-1.142c-.167-.095-.239-.238-.239-.428V5.899c0-2.545 1.95-4.472 4.591-4.472 1 0 1.927.333 2.712.928L8.23 5.067c-.285.166-.428.404-.428.737v6.898zM12 15.128l-2.795-1.57v-3.33L12 8.658l2.795 1.57v3.33L12 15.128zm1.796 7.23c-1 0-1.927-.332-2.712-.927l4.686-2.712c.285-.166.428-.404.428-.737v-6.898l1.974 1.142c.167.095.238.238.238.428v5.233c0 2.545-1.974 4.472-4.614 4.472zm-5.637-5.303l-4.544-2.617c-1.308-.761-2.188-2.378-2.188-3.948A4.482 4.482 0 014.21 6.327v5.423c0 .333.143.571.428.738l5.947 3.449-1.95 1.118a.432.432 0 01-.476 0zm-.262 3.9c-2.688 0-4.662-2.021-4.662-4.519 0-.19.024-.38.047-.57l4.686 2.71c.286.167.571.167.856 0l5.97-3.448v2.26c0 .19-.07.333-.237.428l-4.543 2.616c-.619.357-1.356.523-2.117.523zm5.899 2.83a5.947 5.947 0 005.827-4.756C22.287 18.339 24 15.84 24 13.296c0-1.665-.713-3.282-1.998-4.448.119-.5.19-.999.19-1.498 0-3.401-2.759-5.947-5.946-5.947-.642 0-1.26.095-1.88.31A5.962 5.962 0 0010.205 0a5.947 5.947 0 00-5.827 4.757C1.713 5.447 0 7.945 0 10.49c0 1.666.713 3.283 1.998 4.448-.119.5-.19 1-.19 1.499 0 3.401 2.759 5.946 5.946 5.946.642 0 1.26-.095 1.88-.309a5.96 5.96 0 004.162 1.713z"></path></svg></span><span><b>GPT-6.1 Sol (max)</b><small>OpenAI</small></span></span><span class="num"><small>Score</small><b>0.784</b></span><span class="num"><small>Median cost</small>$2.59</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6.1-sol-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6.1-sol-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6.1-sol-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6.1-sol-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6.1-sol-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gemini-4-argon-high.html"><span class="rk">6</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="url(#c4sGemG5)" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><defs><linearGradient id="c4sGemG5" x1="0" y1="0" x2="1" y2="1"><stop offset="0" stop-color="#4796E3"/><stop offset=".55" stop-color="#9168C0"/><stop offset="1" stop-color="#D96570"/></linearGradient></defs><title>Gemini</title><path d="M20.616 10.835a14.147 14.147 0 01-4.45-3.001 14.111 14.111 0 01-3.678-6.452.503.503 0 00-.975 0 14.134 14.134 0 01-3.679 6.452 14.155 14.155 0 01-4.45 3.001c-.65.28-1.318.505-2.002.678a.502.502 0 000 .975c.684.172 1.35.397 2.002.677a14.147 14.147 0 014.45 3.001 14.112 14.112 0 013.679 6.453.502.502 0 00.975 0c.172-.685.397-1.351.677-2.003a14.145 14.145 0 013.001-4.45 14.113 14.113 0 016.453-3.678.503.503 0 000-.975 13.245 13.245 0 01-2.003-.678z"></path></svg></span><span><b>Gemini 4 Argon (high)</b><small>Google</small></span></span><span class="num"><small>Score</small><b>0.777</b></span><span class="num"><small>Median cost</small>$4.83</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-4-argon-high/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-4-argon-high/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-4-argon-high/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-4-argon-high/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-4-argon-high/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gpt-5.6-sol-max.html"><span class="rk">7</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>OpenAI</title><path d="M9.205 8.658v-2.26c0-.19.072-.333.238-.428l4.543-2.616c.619-.357 1.356-.523 2.117-.523 2.854 0 4.662 2.212 4.662 4.566 0 .167 0 .357-.024.547l-4.71-2.759a.797.797 0 00-.856 0l-5.97 3.473zm10.609 8.8V12.06c0-.333-.143-.57-.429-.737l-5.97-3.473 1.95-1.118a.433.433 0 01.476 0l4.543 2.617c1.309.76 2.189 2.378 2.189 3.948 0 1.808-1.07 3.473-2.76 4.163zM7.802 12.703l-1.95-1.142c-.167-.095-.239-.238-.239-.428V5.899c0-2.545 1.95-4.472 4.591-4.472 1 0 1.927.333 2.712.928L8.23 5.067c-.285.166-.428.404-.428.737v6.898zM12 15.128l-2.795-1.57v-3.33L12 8.658l2.795 1.57v3.33L12 15.128zm1.796 7.23c-1 0-1.927-.332-2.712-.927l4.686-2.712c.285-.166.428-.404.428-.737v-6.898l1.974 1.142c.167.095.238.238.238.428v5.233c0 2.545-1.974 4.472-4.614 4.472zm-5.637-5.303l-4.544-2.617c-1.308-.761-2.188-2.378-2.188-3.948A4.482 4.482 0 014.21 6.327v5.423c0 .333.143.571.428.738l5.947 3.449-1.95 1.118a.432.432 0 01-.476 0zm-.262 3.9c-2.688 0-4.662-2.021-4.662-4.519 0-.19.024-.38.047-.57l4.686 2.71c.286.167.571.167.856 0l5.97-3.448v2.26c0 .19-.07.333-.237.428l-4.543 2.616c-.619.357-1.356.523-2.117.523zm5.899 2.83a5.947 5.947 0 005.827-4.756C22.287 18.339 24 15.84 24 13.296c0-1.665-.713-3.282-1.998-4.448.119-.5.19-.999.19-1.498 0-3.401-2.759-5.947-5.946-5.947-.642 0-1.26.095-1.88.31A5.962 5.962 0 0010.205 0a5.947 5.947 0 00-5.827 4.757C1.713 5.447 0 7.945 0 10.49c0 1.666.713 3.283 1.998 4.448-.119.5-.19 1-.19 1.499 0 3.401 2.759 5.946 5.946 5.946.642 0 1.26-.095 1.88-.309a5.96 5.96 0 004.162 1.713z"></path></svg></span><span><b>GPT-5.6 Sol (max)</b><small>OpenAI</small></span></span><span class="num"><small>Score</small><b>0.723</b></span><span class="num"><small>Median cost</small>$6.87</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-5.6-sol-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-5.6-sol-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-5.6-sol-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-5.6-sol-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-5.6-sol-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/claude-haiku-5.5-max.html"><span class="rk">8</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#D97757" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Claude</title><path d="M4.709 15.955l4.72-2.647.08-.23-.08-.128H9.2l-.79-.048-2.698-.073-2.339-.097-2.266-.122-.571-.121L0 11.784l.055-.352.48-.321.686.06 1.52.103 2.278.158 1.652.097 2.449.255h.389l.055-.157-.134-.098-.103-.097-2.358-1.596-2.552-1.688-1.336-.972-.724-.491-.364-.462-.158-1.008.656-.722.881.06.225.061.893.686 1.908 1.476 2.491 1.833.365.304.145-.103.019-.073-.164-.274-1.355-2.446-1.446-2.49-.644-1.032-.17-.619a2.97 2.97 0 01-.104-.729L6.283.134 6.696 0l.996.134.42.364.62 1.414 1.002 2.229 1.555 3.03.456.898.243.832.091.255h.158V9.01l.128-1.706.237-2.095.23-2.695.08-.76.376-.91.747-.492.584.28.48.685-.067.444-.286 1.851-.559 2.903-.364 1.942h.212l.243-.242.985-1.306 1.652-2.064.73-.82.85-.904.547-.431h1.033l.76 1.129-.34 1.166-1.064 1.347-.881 1.142-1.264 1.7-.79 1.36.073.11.188-.02 2.856-.606 1.543-.28 1.841-.315.833.388.091.395-.328.807-1.969.486-2.309.462-3.439.813-.042.03.049.061 1.549.146.662.036h1.622l3.02.225.79.522.474.638-.079.485-1.215.62-1.64-.389-3.829-.91-1.312-.329h-.182v.11l1.093 1.068 2.006 1.81 2.509 2.33.127.578-.322.455-.34-.049-2.205-1.657-.851-.747-1.926-1.62h-.128v.17l.444.649 2.345 3.521.122 1.08-.17.353-.608.213-.668-.122-1.374-1.925-1.415-2.167-1.143-1.943-.14.08-.674 7.254-.316.37-.729.28-.607-.461-.322-.747.322-1.476.389-1.924.315-1.53.286-1.9.17-.632-.012-.042-.14.018-1.434 1.967-2.18 2.945-1.726 1.845-.414.164-.717-.37.067-.662.401-.589 2.388-3.036 1.44-1.882.93-1.086-.006-.158h-.055L4.132 18.56l-1.13.146-.487-.456.061-.746.231-.243 1.908-1.312-.006.006z"></path></svg></span><span><b>Claude Haiku 5.5 (max)</b><small>Anthropic</small></span></span><span class="num"><small>Score</small><b>0.718</b></span><span class="num"><small>Median cost</small>$2.43</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-haiku-5.5-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-haiku-5.5-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-haiku-5.5-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-haiku-5.5-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/claude-haiku-5.5-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/muse-wonder-full-1.0-max.html"><span class="rk">9</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#0081FB" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Meta</title><path d="M6.897 4c1.915 0 3.516.932 5.43 3.376l.282-.373c.19-.246.383-.484.58-.71l.313-.35C14.588 4.788 15.792 4 17.225 4c1.273 0 2.469.557 3.491 1.516l.218.213c1.73 1.765 2.917 4.71 3.053 8.026l.011.392.002.25c0 1.501-.28 2.759-.818 3.7l-.14.23-.108.153c-.301.42-.664.758-1.086 1.009l-.265.142-.087.04a3.493 3.493 0 01-.302.118 4.117 4.117 0 01-1.33.208c-.524 0-.996-.067-1.438-.215-.614-.204-1.163-.56-1.726-1.116l-.227-.235c-.753-.812-1.534-1.976-2.493-3.586l-1.43-2.41-.544-.895-1.766 3.13-.343.592C7.597 19.156 6.227 20 4.356 20c-1.21 0-2.205-.42-2.936-1.182l-.168-.184c-.484-.573-.837-1.311-1.043-2.189l-.067-.32a8.69 8.69 0 01-.136-1.288L0 14.468c.002-.745.06-1.49.174-2.23l.1-.573c.298-1.53.828-2.958 1.536-4.157l.209-.34c1.177-1.83 2.789-3.053 4.615-3.16L6.897 4zm-.033 2.615l-.201.01c-.83.083-1.606.673-2.252 1.577l-.138.199-.01.018c-.67 1.017-1.185 2.378-1.456 3.845l-.004.022a12.591 12.591 0 00-.207 2.254l.002.188c.004.18.017.36.04.54l.043.291c.092.503.257.908.486 1.208l.117.137c.303.323.698.492 1.17.492 1.1 0 1.796-.676 3.696-3.641l2.175-3.4.454-.701-.139-.198C9.11 7.3 8.084 6.616 6.864 6.616zm10.196-.552l-.176.007c-.635.048-1.223.359-1.82.933l-.196.198c-.439.462-.887 1.064-1.367 1.807l.266.398c.18.274.362.56.55.858l.293.475 1.396 2.335.695 1.114c.583.926 1.03 1.6 1.408 2.082l.213.262c.282.326.529.54.777.673l.102.05c.227.1.457.138.718.138.176.002.35-.023.518-.073.338-.104.61-.32.813-.637l.095-.163.077-.162c.194-.459.29-1.06.29-1.785l-.006-.449c-.08-2.871-.938-5.372-2.2-6.798l-.176-.189c-.67-.683-1.444-1.074-2.27-1.074z"></path></svg></span><span><b>Muse Wonder Full 1.0 (max)</b><small>Meta</small></span></span><span class="num"><small>Score</small><b>0.715</b></span><span class="num" title="Muse Wonder Full 1.0 (max): sold by subscription; cost = the token counts its CLI logs, at Muse Wonder&#x27;s per-token list price"><small>Median cost</small>$3.66*</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-wonder-full-1.0-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-wonder-full-1.0-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-wonder-full-1.0-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-wonder-full-1.0-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-wonder-full-1.0-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gemini-3.8-flash-high.html"><span class="rk">10</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="url(#c4sGemG9)" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><defs><linearGradient id="c4sGemG9" x1="0" y1="0" x2="1" y2="1"><stop offset="0" stop-color="#4796E3"/><stop offset=".55" stop-color="#9168C0"/><stop offset="1" stop-color="#D96570"/></linearGradient></defs><title>Gemini</title><path d="M20.616 10.835a14.147 14.147 0 01-4.45-3.001 14.111 14.111 0 01-3.678-6.452.503.503 0 00-.975 0 14.134 14.134 0 01-3.679 6.452 14.155 14.155 0 01-4.45 3.001c-.65.28-1.318.505-2.002.678a.502.502 0 000 .975c.684.172 1.35.397 2.002.677a14.147 14.147 0 014.45 3.001 14.112 14.112 0 013.679 6.453.502.502 0 00.975 0c.172-.685.397-1.351.677-2.003a14.145 14.145 0 013.001-4.45 14.113 14.113 0 016.453-3.678.503.503 0 000-.975 13.245 13.245 0 01-2.003-.678z"></path></svg></span><span><b>Gemini 3.8 Flash (high)</b><small>Google</small></span></span><span class="num"><small>Score</small><b>0.694</b></span><span class="num"><small>Median cost</small>$3.85</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-3.8-flash-high/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-3.8-flash-high/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-3.8-flash-high/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-3.8-flash-high/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemini-3.8-flash-high/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gpt-6-luna-max.html"><span class="rk">11</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>OpenAI</title><path d="M9.205 8.658v-2.26c0-.19.072-.333.238-.428l4.543-2.616c.619-.357 1.356-.523 2.117-.523 2.854 0 4.662 2.212 4.662 4.566 0 .167 0 .357-.024.547l-4.71-2.759a.797.797 0 00-.856 0l-5.97 3.473zm10.609 8.8V12.06c0-.333-.143-.57-.429-.737l-5.97-3.473 1.95-1.118a.433.433 0 01.476 0l4.543 2.617c1.309.76 2.189 2.378 2.189 3.948 0 1.808-1.07 3.473-2.76 4.163zM7.802 12.703l-1.95-1.142c-.167-.095-.239-.238-.239-.428V5.899c0-2.545 1.95-4.472 4.591-4.472 1 0 1.927.333 2.712.928L8.23 5.067c-.285.166-.428.404-.428.737v6.898zM12 15.128l-2.795-1.57v-3.33L12 8.658l2.795 1.57v3.33L12 15.128zm1.796 7.23c-1 0-1.927-.332-2.712-.927l4.686-2.712c.285-.166.428-.404.428-.737v-6.898l1.974 1.142c.167.095.238.238.238.428v5.233c0 2.545-1.974 4.472-4.614 4.472zm-5.637-5.303l-4.544-2.617c-1.308-.761-2.188-2.378-2.188-3.948A4.482 4.482 0 014.21 6.327v5.423c0 .333.143.571.428.738l5.947 3.449-1.95 1.118a.432.432 0 01-.476 0zm-.262 3.9c-2.688 0-4.662-2.021-4.662-4.519 0-.19.024-.38.047-.57l4.686 2.71c.286.167.571.167.856 0l5.97-3.448v2.26c0 .19-.07.333-.237.428l-4.543 2.616c-.619.357-1.356.523-2.117.523zm5.899 2.83a5.947 5.947 0 005.827-4.756C22.287 18.339 24 15.84 24 13.296c0-1.665-.713-3.282-1.998-4.448.119-.5.19-.999.19-1.498 0-3.401-2.759-5.947-5.946-5.947-.642 0-1.26.095-1.88.31A5.962 5.962 0 0010.205 0a5.947 5.947 0 00-5.827 4.757C1.713 5.447 0 7.945 0 10.49c0 1.666.713 3.283 1.998 4.448-.119.5-.19 1-.19 1.499 0 3.401 2.759 5.946 5.946 5.946.642 0 1.26-.095 1.88-.309a5.96 5.96 0 004.162 1.713z"></path></svg></span><span><b>GPT-6 Luna (max)</b><small>OpenAI</small></span></span><span class="num"><small>Score</small><b>0.688</b></span><span class="num"><small>Median cost</small>$0.16</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-luna-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-luna-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-luna-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-luna-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gpt-6-luna-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/grok-4.6-xhigh.html"><span class="rk">12</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Grok</title><path d="M9.27 15.29l7.978-5.897c.391-.29.95-.177 1.137.272.98 2.369.542 5.215-1.41 7.169-1.951 1.954-4.667 2.382-7.149 1.406l-2.711 1.257c3.889 2.661 8.611 2.003 11.562-.953 2.341-2.344 3.066-5.539 2.388-8.42l.006.007c-.983-4.232.242-5.924 2.75-9.383.06-.082.12-.164.179-.248l-3.301 3.305v-.01L9.267 15.292M7.623 16.723c-2.792-2.67-2.31-6.801.071-9.184 1.761-1.763 4.647-2.483 7.166-1.425l2.705-1.25a7.808 7.808 0 00-1.829-1A8.975 8.975 0 005.984 5.83c-2.533 2.536-3.33 6.436-1.962 9.764 1.022 2.487-.653 4.246-2.34 6.022-.599.63-1.199 1.259-1.682 1.925l7.62-6.815"></path></svg></span><span><b>Grok 4.6 (xhigh)</b><small>xAI</small></span></span><span class="num"><small>Score</small><b>0.625</b></span><span class="num"><small>Median cost</small>$7.41</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.6-xhigh/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.6-xhigh/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.6-xhigh/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.6-xhigh/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.6-xhigh/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/muse-spark-open-max.html"><span class="rk">13</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#0081FB" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Meta</title><path d="M6.897 4c1.915 0 3.516.932 5.43 3.376l.282-.373c.19-.246.383-.484.58-.71l.313-.35C14.588 4.788 15.792 4 17.225 4c1.273 0 2.469.557 3.491 1.516l.218.213c1.73 1.765 2.917 4.71 3.053 8.026l.011.392.002.25c0 1.501-.28 2.759-.818 3.7l-.14.23-.108.153c-.301.42-.664.758-1.086 1.009l-.265.142-.087.04a3.493 3.493 0 01-.302.118 4.117 4.117 0 01-1.33.208c-.524 0-.996-.067-1.438-.215-.614-.204-1.163-.56-1.726-1.116l-.227-.235c-.753-.812-1.534-1.976-2.493-3.586l-1.43-2.41-.544-.895-1.766 3.13-.343.592C7.597 19.156 6.227 20 4.356 20c-1.21 0-2.205-.42-2.936-1.182l-.168-.184c-.484-.573-.837-1.311-1.043-2.189l-.067-.32a8.69 8.69 0 01-.136-1.288L0 14.468c.002-.745.06-1.49.174-2.23l.1-.573c.298-1.53.828-2.958 1.536-4.157l.209-.34c1.177-1.83 2.789-3.053 4.615-3.16L6.897 4zm-.033 2.615l-.201.01c-.83.083-1.606.673-2.252 1.577l-.138.199-.01.018c-.67 1.017-1.185 2.378-1.456 3.845l-.004.022a12.591 12.591 0 00-.207 2.254l.002.188c.004.18.017.36.04.54l.043.291c.092.503.257.908.486 1.208l.117.137c.303.323.698.492 1.17.492 1.1 0 1.796-.676 3.696-3.641l2.175-3.4.454-.701-.139-.198C9.11 7.3 8.084 6.616 6.864 6.616zm10.196-.552l-.176.007c-.635.048-1.223.359-1.82.933l-.196.198c-.439.462-.887 1.064-1.367 1.807l.266.398c.18.274.362.56.55.858l.293.475 1.396 2.335.695 1.114c.583.926 1.03 1.6 1.408 2.082l.213.262c.282.326.529.54.777.673l.102.05c.227.1.457.138.718.138.176.002.35-.023.518-.073.338-.104.61-.32.813-.637l.095-.163.077-.162c.194-.459.29-1.06.29-1.785l-.006-.449c-.08-2.871-.938-5.372-2.2-6.798l-.176-.189c-.67-.683-1.444-1.074-2.27-1.074z"></path></svg></span><span><b>Muse Spark Open (max)</b><small>Meta</small></span></span><span class="num"><small>Score</small><b>0.611</b></span><span class="num"><small>Median cost</small>$2.01</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-open-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-open-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-open-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-open-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-open-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/muse-spark-1.3-max.html"><span class="rk">14</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#0081FB" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Meta</title><path d="M6.897 4c1.915 0 3.516.932 5.43 3.376l.282-.373c.19-.246.383-.484.58-.71l.313-.35C14.588 4.788 15.792 4 17.225 4c1.273 0 2.469.557 3.491 1.516l.218.213c1.73 1.765 2.917 4.71 3.053 8.026l.011.392.002.25c0 1.501-.28 2.759-.818 3.7l-.14.23-.108.153c-.301.42-.664.758-1.086 1.009l-.265.142-.087.04a3.493 3.493 0 01-.302.118 4.117 4.117 0 01-1.33.208c-.524 0-.996-.067-1.438-.215-.614-.204-1.163-.56-1.726-1.116l-.227-.235c-.753-.812-1.534-1.976-2.493-3.586l-1.43-2.41-.544-.895-1.766 3.13-.343.592C7.597 19.156 6.227 20 4.356 20c-1.21 0-2.205-.42-2.936-1.182l-.168-.184c-.484-.573-.837-1.311-1.043-2.189l-.067-.32a8.69 8.69 0 01-.136-1.288L0 14.468c.002-.745.06-1.49.174-2.23l.1-.573c.298-1.53.828-2.958 1.536-4.157l.209-.34c1.177-1.83 2.789-3.053 4.615-3.16L6.897 4zm-.033 2.615l-.201.01c-.83.083-1.606.673-2.252 1.577l-.138.199-.01.018c-.67 1.017-1.185 2.378-1.456 3.845l-.004.022a12.591 12.591 0 00-.207 2.254l.002.188c.004.18.017.36.04.54l.043.291c.092.503.257.908.486 1.208l.117.137c.303.323.698.492 1.17.492 1.1 0 1.796-.676 3.696-3.641l2.175-3.4.454-.701-.139-.198C9.11 7.3 8.084 6.616 6.864 6.616zm10.196-.552l-.176.007c-.635.048-1.223.359-1.82.933l-.196.198c-.439.462-.887 1.064-1.367 1.807l.266.398c.18.274.362.56.55.858l.293.475 1.396 2.335.695 1.114c.583.926 1.03 1.6 1.408 2.082l.213.262c.282.326.529.54.777.673l.102.05c.227.1.457.138.718.138.176.002.35-.023.518-.073.338-.104.61-.32.813-.637l.095-.163.077-.162c.194-.459.29-1.06.29-1.785l-.006-.449c-.08-2.871-.938-5.372-2.2-6.798l-.176-.189c-.67-.683-1.444-1.074-2.27-1.074z"></path></svg></span><span><b>Muse Spark 1.3 (max)</b><small>Meta</small></span></span><span class="num"><small>Score</small><b>0.548</b></span><span class="num"><small>Median cost</small>$0.23</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-1.3-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-1.3-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-1.3-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-1.3-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/muse-spark-1.3-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/glm-5.3-flash-max.html"><span class="rk">15</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Z.ai</title><path d="M12.105 2L9.927 4.953H.653L2.83 2h9.276zM23.254 19.048L21.078 22h-9.242l2.174-2.952h9.244zM24 2L9.264 22H0L14.736 2H24z"></path></svg></span><span><b>GLM-5.3 Flash (max)</b><small>Z.ai</small></span></span><span class="num"><small>Score</small><b>0.542</b></span><span class="num"><small>Median cost</small>$0.94</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/glm-5.3-flash-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/glm-5.3-flash-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/glm-5.3-flash-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/glm-5.3-flash-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/glm-5.3-flash-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/grok-4.7-xhigh.html"><span class="rk">16</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="currentColor" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Grok</title><path d="M9.27 15.29l7.978-5.897c.391-.29.95-.177 1.137.272.98 2.369.542 5.215-1.41 7.169-1.951 1.954-4.667 2.382-7.149 1.406l-2.711 1.257c3.889 2.661 8.611 2.003 11.562-.953 2.341-2.344 3.066-5.539 2.388-8.42l.006.007c-.983-4.232.242-5.924 2.75-9.383.06-.082.12-.164.179-.248l-3.301 3.305v-.01L9.267 15.292M7.623 16.723c-2.792-2.67-2.31-6.801.071-9.184 1.761-1.763 4.647-2.483 7.166-1.425l2.705-1.25a7.808 7.808 0 00-1.829-1A8.975 8.975 0 005.984 5.83c-2.533 2.536-3.33 6.436-1.962 9.764 1.022 2.487-.653 4.246-2.34 6.022-.599.63-1.199 1.259-1.682 1.925l7.62-6.815"></path></svg></span><span><b>Grok 4.7 (xhigh)</b><small>xAI</small></span></span><span class="num"><small>Score</small><b>0.541</b></span><span class="num"><small>Median cost</small>$7.29</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.7-xhigh/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.7-xhigh/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.7-xhigh/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.7-xhigh/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/grok-4.7-xhigh/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/mimo-v2.6-pro-max.html"><span class="rk">17</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#FF6900" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>Xiaomi</title><path d="M12 0C8.016 0 4.756.255 2.493 2.516.23 4.776 0 8.033 0 12.012c0 3.98.23 7.235 2.494 9.497C4.757 23.77 8.017 24 12 24c3.983 0 7.243-.23 9.506-2.491C23.77 19.247 24 15.99 24 12.012c0-3.984-.233-7.243-2.502-9.504C19.234.252 15.978 0 12 0zM4.906 7.405h5.624c1.47 0 3.007.068 3.764.827.746.746.827 2.233.83 3.676v4.54a.15.15 0 0 1-.152.147h-1.947a.15.15 0 0 1-.152-.148V11.83c-.002-.806-.048-1.634-.464-2.051-.358-.36-1.026-.441-1.72-.458H7.158a.15.15 0 0 0-.151.147v6.98a.15.15 0 0 1-.152.148H4.906a.15.15 0 0 1-.15-.148V7.554a.15.15 0 0 1 .15-.149zm12.131 0h1.949a.15.15 0 0 1 .15.15v8.892a.15.15 0 0 1-.15.148h-1.949a.15.15 0 0 1-.151-.148V7.554a.15.15 0 0 1 .151-.149zM8.92 10.948h2.046c.083 0 .15.066.15.147v5.352a.15.15 0 0 1-.15.148H8.92a.15.15 0 0 1-.152-.148v-5.352a.15.15 0 0 1 .152-.147Z"/></svg></span><span><b>MiMo V2.6 Pro (max)</b><small>Xiaomi</small></span></span><span class="num"><small>Score</small><b>0.527</b></span><span class="num"><small>Median cost</small>$0.92</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/mimo-v2.6-pro-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/mimo-v2.6-pro-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/mimo-v2.6-pro-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/mimo-v2.6-pro-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/mimo-v2.6-pro-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/gemma-4-31b-thinking-on.html"><span class="rk">18</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="url(#c4sGemG17)" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><defs><linearGradient id="c4sGemG17" x1="0" y1="0" x2="1" y2="1"><stop offset="0" stop-color="#4796E3"/><stop offset=".55" stop-color="#9168C0"/><stop offset="1" stop-color="#D96570"/></linearGradient></defs><title>Gemini</title><path d="M20.616 10.835a14.147 14.147 0 01-4.45-3.001 14.111 14.111 0 01-3.678-6.452.503.503 0 00-.975 0 14.134 14.134 0 01-3.679 6.452 14.155 14.155 0 01-4.45 3.001c-.65.28-1.318.505-2.002.678a.502.502 0 000 .975c.684.172 1.35.397 2.002.677a14.147 14.147 0 014.45 3.001 14.112 14.112 0 013.679 6.453.502.502 0 00.975 0c.172-.685.397-1.351.677-2.003a14.145 14.145 0 013.001-4.45 14.113 14.113 0 016.453-3.678.503.503 0 000-.975 13.245 13.245 0 01-2.003-.678z"></path></svg></span><span><b>Gemma 4 31B (thinking on)</b><small>Google</small></span></span><span class="num"><small>Score</small><b>0.517</b></span><span class="num" title="Gemma 4 31B (thinking on): self-hosted; cost = the token counts its agent logs, at Gemma 4 31B&#x27;s OpenRouter list price ($0.20 input, $0.40 output per million)"><small>Median cost</small>$0.06*</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/gemma-4-31b-thinking-on/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemma-4-31b-thinking-on/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemma-4-31b-thinking-on/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemma-4-31b-thinking-on/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/gemma-4-31b-thinking-on/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li><li><a class="gal-agent" href="model/deepseek-v4.1-flash-max.html"><span class="rk">19</span><span class="who"><span class="logo" aria-hidden="true"><svg fill="#4D6BFE" fill-rule="evenodd"  viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><title>DeepSeek</title><path d="M23.748 4.482c-.254-.124-.364.113-.512.234-.051.039-.094.09-.137.136-.372.397-.806.657-1.373.626-.829-.046-1.537.214-2.163.848-.133-.782-.575-1.248-1.247-1.548-.352-.156-.708-.311-.955-.65-.172-.241-.219-.51-.305-.774-.055-.16-.11-.323-.293-.35-.2-.031-.278.136-.356.276-.313.572-.434 1.202-.422 1.84.027 1.436.633 2.58 1.838 3.393.137.093.172.187.129.323-.082.28-.18.552-.266.833-.055.179-.137.217-.329.14a5.526 5.526 0 01-1.736-1.18c-.857-.828-1.631-1.742-2.597-2.458a11.365 11.365 0 00-.689-.471c-.985-.957.13-1.743.388-1.836.27-.098.093-.432-.779-.428-.872.004-1.67.295-2.687.684a3.055 3.055 0 01-.465.137 9.597 9.597 0 00-2.883-.102c-1.885.21-3.39 1.102-4.497 2.623C.082 8.606-.231 10.684.152 12.85c.403 2.284 1.569 4.175 3.36 5.653 1.858 1.533 3.997 2.284 6.438 2.14 1.482-.085 3.133-.284 4.994-1.86.47.234.962.327 1.78.397.63.059 1.236-.03 1.705-.128.735-.156.684-.837.419-.961-2.155-1.004-1.682-.595-2.113-.926 1.096-1.296 2.746-2.642 3.392-7.003.05-.347.007-.565 0-.845-.004-.17.035-.237.23-.256a4.173 4.173 0 001.545-.475c1.396-.763 1.96-2.015 2.093-3.517.02-.23-.004-.467-.247-.588zM11.581 18c-2.089-1.642-3.102-2.183-3.52-2.16-.392.024-.321.471-.235.763.09.288.207.486.371.739.114.167.192.416-.113.603-.673.416-1.842-.14-1.897-.167-1.361-.802-2.5-1.86-3.301-3.307-.774-1.393-1.224-2.887-1.298-4.482-.02-.386.093-.522.477-.592a4.696 4.696 0 011.529-.039c2.132.312 3.946 1.265 5.468 2.774.868.86 1.525 1.887 2.202 2.891.72 1.066 1.494 2.082 2.48 2.914.348.292.625.514.891.677-.802.09-2.14.11-3.054-.614zm1-6.44a.306.306 0 01.415-.287.302.302 0 01.2.288.306.306 0 01-.31.307.303.303 0 01-.304-.308zm3.11 1.596c-.2.081-.399.151-.59.16a1.245 1.245 0 01-.798-.254c-.274-.23-.47-.358-.552-.758a1.73 1.73 0 01.016-.588c.07-.327-.008-.537-.239-.727-.187-.156-.426-.199-.688-.199a.559.559 0 01-.254-.078c-.11-.054-.2-.19-.114-.358.028-.054.16-.186.192-.21.356-.202.767-.136 1.146.016.352.144.618.408 1.001.782.391.451.462.576.685.914.176.265.336.537.445.848.067.195-.019.354-.25.452z"></path></svg></span><span><b>DeepSeek V4.1 Flash (max)</b><small>DeepSeek</small></span></span><span class="num"><small>Score</small><b>0.366</b></span><span class="num"><small>Median cost</small>$0.35</span><span class="strip" aria-hidden="true"><img alt="" decoding="async" height="270" loading="lazy" src="img/deepseek-v4.1-flash-max/blue-city/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/deepseek-v4.1-flash-max/cyberpunk/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/deepseek-v4.1-flash-max/egyptian-temple/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/deepseek-v4.1-flash-max/nordic-harbour/v0_t.webp?v=20261016t2s" width="480"/><img alt="" decoding="async" height="270" loading="lazy" src="img/deepseek-v4.1-flash-max/winter-town/v0_t.webp?v=20261016t2s" width="480"/></span></a></li></ol></div></section>
 </main>
 <footer><p>Code4Scene  ·  UC San Diego &amp; UC Berkeley  ·  <a href="https://arxiv.org/abs/2609.36777" rel="noopener" target="_blank">arXiv:2609.36777</a>  ·  <a href="https://github.com/SimWorld-AI/Code4Scene" rel="noopener" target="_blank">GitHub</a>  ·  <a href="https://simworld.org/" rel="noopener" target="_blank">SimWorld Home</a></p></footer>
 <script defer src="../assets/gallery.js?v=20261016t2s"></script>

gallery/model/gemma-4-31b-thinking-on.html CHANGED Viewed

The diff for this file is too large to render. See raw diff

index.html CHANGED Viewed

The diff for this file is too large to render. See raw diff

scripts/t2s_sandbox_round.py CHANGED Viewed

@@ -87,6 +87,10 @@ TITLES = {
 TRACE_COSTS = {
     "musewf10-max-t2s20": ("musewf_cost.json",
                            "sold by subscription; cost = the token counts its CLI logs, at Muse Wonder's per-token list price"),
 }
 # the comparison videos' line-up (internal video/stack_video.py), in the order they are drawn
 VIDEO_MODELS = ["Claude Opus 5.5 (max)", "GPT-6 Astra (max)", "GPT-6.1 Sol (max)", "Gemini 4 Argon (high)"]

 TRACE_COSTS = {
     "musewf10-max-t2s20": ("musewf_cost.json",
                            "sold by subscription; cost = the token counts its CLI logs, at Muse Wonder's per-token list price"),
+    # self-hosted, so nothing was billed (user, 2026-10-16: "Gemma的价格可以估算一下？"); scripts/t2s_token_cost.py
+    "gemma4-think-public95": ("gemma4think_cost.json",
+                              "self-hosted; cost = the token counts its agent logs, at Gemma 4 31B's OpenRouter list price "
+                              "($0.20 input, $0.40 output per million)"),
 }
 # the comparison videos' line-up (internal video/stack_video.py), in the order they are drawn
 VIDEO_MODELS = ["Claude Opus 5.5 (max)", "GPT-6 Astra (max)", "GPT-6.1 Sol (max)", "Gemini 4 Argon (high)"]

scripts/t2s_token_cost.py ADDED Viewed

	@@ -0,0 +1,54 @@

+#!/usr/bin/env python3
+"""Per-case cost of a self-hosted Text-to-Scene run from the token counts its agent logged (user, 2026-10-16:
+"Gemma的价格可以估算一下？").
+The OpenRouter-loop agent writes every model call's usage to <attempt>/episode/openrouter_r*_raw.jsonl
+(`llm_request` items: input_tokens, cached_input_tokens, output_tokens, which include reasoning_output_tokens).
+A self-hosted model is not billed (cost_usd_micros 0), so the internal table has no cost for it; this prices the
+logged tokens at the model's OpenRouter list price. The kept attempt of each case is <run_dir>/cases/<case>/final,
+as for every other model. Read-only; JSON on stdout:
+    ssh <host> python3 - <in $/M> <cached in $/M> <out $/M> <run_dir> ... < scripts/t2s_token_cost.py > ../t2s-src/<name>_cost.json
+"""
+import glob
+import json
+import os
+import statistics
+import sys
+P_IN, P_CACHED, P_OUT = (float(x) for x in sys.argv[1:4])
+RUNS = sys.argv[4:]
+out, problems = {}, []
+for rd in RUNS:
+    for cdir in sorted(glob.glob(os.path.join(rd, "cases", "*-long"))):
+        case = os.path.basename(cdir)
+        att = os.path.realpath(os.path.join(cdir, "final"))
+        streams = sorted(glob.glob(os.path.join(att, "episode", "openrouter_r*_raw.jsonl")))
+        if not streams:
+            continue
+        tok = {"input": 0, "cached": 0, "output": 0, "reasoning": 0}
+        calls = 0
+        for path in streams:
+            for line in open(path, errors="ignore"):
+                if '"llm_request"' not in line:
+                    continue
+                try:
+                    item = json.loads(line).get("item") or {}
+                except ValueError:
+                    continue
+                u = item.get("usage") if item.get("type") == "llm_request" else None
+                if not u:
+                    continue
+                inp, cached, outp, rsn = (int(u.get(k) or 0) for k in
+                                          ("input_tokens", "cached_input_tokens", "output_tokens", "reasoning_output_tokens"))
+                if cached > inp or rsn > outp:
+                    problems.append("%s: usage outside the checked semantics %s" % (case, u))
+                tok["input"] += inp; tok["cached"] += cached; tok["output"] += outp; tok["reasoning"] += rsn
+                calls += 1
+        usd = ((tok["input"] - tok["cached"]) * P_IN + tok["cached"] * P_CACHED + tok["output"] * P_OUT) / 1e6
+        if not calls:
+            problems.append("%s: no logged usage in %s" % (case, att))
+        out[case] = {"attempt": att, "calls": calls, "tokens": tok, "cost_usd": round(usd, 6) if calls else None}
+costs = [v["cost_usd"] for v in out.values() if v["cost_usd"] is not None]
+json.dump({"method": __doc__, "prices_per_million": [P_IN, P_CACHED, P_OUT], "cases": out, "problems": problems,
+           "median_cost_usd": statistics.median(costs) if costs else None, "n": len(costs)}, sys.stdout, indent=1)