Results
Pass rate is passes / judged runs. Cost, time, and unjudged runs stay visible beside it.
36 models · 27 with judged runs · 494 runs · 157 judged · updated 8 Oct 2026 · ordered by pass rate
Pass rate: passes / judged runs
Lighter bars: fewer than 3 judged runs
36 models shown, ordered by pass rate. 494 runs match the search.passes / judged runs.
Every run, cost × time.
Compare individual model runs without flattening them into an average. The lower-left region is lower-cost and faster.
Each dot is one public run. Cost runs left to right; wall-clock time runs bottom to top. Logarithmic spacing keeps the full range legible.
106 unplotted runs
Claude Opus 5.5 — CARVE lacks measured cost or time · Claude Opus 5.5 — Courtyard Blossom Stage 2 lacks measured cost or time · Claude Opus 5.5 — Courtyard Blossom Stage 2 lacks measured cost or time · Claude Opus 5.5 — Doom lacks measured cost or time · Claude Opus 5.5 — Explorable space-flight game lacks measured cost or time · Claude Opus 5.5 — High-voxel-density Jungle Temple diorama lacks measured cost or time · Claude Opus 5.5 — High-voxel-density Jungle Temple diorama lacks measured cost or time · Claude Opus 5.5 — High-voxel-density Oasis Outpost diorama lacks measured cost or time · Claude Opus 5.5 — High-voxel-density Oasis Outpost diorama lacks measured cost or time · Claude Opus 5.5 — Infinite cathedral corridor shader lacks measured cost or time · Claude Opus 5.5 — JRPG boss battle lacks measured cost or time · Claude Opus 5.5 — Neo-gothic storm city shader lacks measured cost or time · Claude Opus 5.5 — Neo-gothic storm city shader lacks measured cost or time · Claude Opus 5.5 — Neo-gothic storm city shader lacks measured cost or time · Claude Opus 5.5 — Neon Gunner lacks measured cost or time · Claude Opus 5.5 — Sekiro Main Menu lacks measured cost or time · Claude Opus 5.5 — Sekiro Main Menu lacks measured cost or time · Claude Opus 5.5 — Space Flight Stage 2 — Landfall lacks measured cost or time · GPT-6 Astra — ATS Depot Driving lacks measured cost or time · GPT-6 Astra — Bluetooth Speaker PCB lacks measured cost or time · GPT-6 Astra — Campfire under the stars lacks measured cost or time · GPT-6 Astra — Courtyard Blossom Stage 2 lacks measured cost or time · GPT-6 Astra — Doom lacks measured cost or time · GPT-6 Astra — High-voxel-density Jungle Temple diorama lacks measured cost or time · GPT-6 Astra — Space Flight Stage 2 — Landfall lacks measured cost or time · GPT-5.6 Luna — Apple Carry lacks measured cost or time · GPT-5.6 Luna — Apple Carry lacks measured cost or time · GPT-5.6 Luna — Campfire under the stars Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · GPT-5.6 Luna — Courtyard Blossom Stage 2 Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · GPT-5.6 Luna — ECHO Main Menu Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · GPT-5.6 Luna — High-voxel-density Oasis Outpost diorama Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · GPT-5.6 Luna — Infinite cathedral corridor shader Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · GPT-5.6 Luna — Interactive Three.js voxel map viewer Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · GPT-5.6 Luna — JRPG boss battle Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · GPT-5.6 Luna — Neo-gothic storm city shader Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · GPT-5.6 Luna — Neon Gunner Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · GPT-5.6 Luna — Sekiro Main Menu Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · GPT-5.6 Luna — The Last of Us Main Menu Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · Grok 4.6 — Apple Stem lacks measured cost or time · Grok 4.6 — Off-road Mud Game Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · DeepSeek V4 Flash — Campfire under the stars lacks measured cost or time · DeepSeek V4 Flash — Courtyard Blossom Stage 2 lacks measured cost or time · DeepSeek V4 Flash — ECHO Main Menu lacks measured cost or time · DeepSeek V4 Flash — High-voxel-density Oasis Outpost diorama lacks measured cost or time · DeepSeek V4 Flash — Infinite cathedral corridor shader lacks measured cost or time · DeepSeek V4 Flash — Interactive Three.js voxel map viewer lacks measured cost or time · DeepSeek V4 Flash — JRPG boss battle lacks measured cost or time · DeepSeek V4 Flash — Neo-gothic storm city shader lacks measured cost or time · DeepSeek V4 Flash — Neon Gunner lacks measured cost or time · DeepSeek V4 Flash — Sekiro Main Menu lacks measured cost or time · DeepSeek V4 Flash — The Last of Us Main Menu lacks measured cost or time · GPT-6 Sol — Campfire under the stars lacks measured cost or time · GPT-6 Sol — CARVE lacks measured cost or time · GPT-6 Sol — Courtyard Blossom Stage 2 lacks measured cost or time · GPT-6 Sol — High-voxel-density Jungle Temple diorama lacks measured cost or time · GPT-6 Sol — High-voxel-density Oasis Outpost diorama lacks measured cost or time · GPT-6 Sol — High-voxel-density Shrine Village diorama lacks measured cost or time · GPT-6 Sol — Infinite cathedral corridor shader lacks measured cost or time · GPT-6 Sol — JRPG boss battle lacks measured cost or time · GPT-6 Sol — Neo-gothic storm city shader lacks measured cost or time · GPT-6 Sol — Neon Gunner lacks measured cost or time · GPT-6 Sol — Sekiro Main Menu lacks measured cost or time · GPT-6 Sol — The Last of Us Main Menu lacks measured cost or time · GPT-6.1 Sol — Bluetooth Speaker PCB lacks measured cost or time · GPT-6.1 Sol — CAD-002 Robot Arm lacks measured cost or time · GPT-6.1 Sol — Turbofan Engine lacks measured cost or time · Grok 4.7 — Campfire under the stars lacks measured cost or time · Grok 4.7 — CARVE lacks measured cost or time · Grok 4.7 — Courtyard Blossom Stage 2 lacks measured cost or time · Grok 4.7 — Explorable space-flight game lacks measured cost or time · Grok 4.7 — High-voxel-density Oasis Outpost diorama lacks measured cost or time · Grok 4.7 — Infinite cathedral corridor shader lacks measured cost or time · Grok 4.7 — JRPG boss battle lacks measured cost or time · Grok 4.7 — Neo-gothic storm city shader lacks measured cost or time · Grok 4.7 — Neon Gunner lacks measured cost or time · Grok 4.7 — Sekiro Main Menu lacks measured cost or time · Grok 4.7 — Space Flight Stage 2 — Landfall lacks measured cost or time · Grok 4.7 — The Last of Us Main Menu lacks measured cost or time · Kimi K3 — Neon Gunner Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · Kimi K3 — Sekiro Main Menu Measured or estimated cost is unavailable; excluded from cost averages and the cost × time plot. · Kimi K3 — The Last of Us Main Menu Non-USD cost; excluded from USD averages and the cost × time plot. · Claude Fable 5 — Neo-gothic storm city shader lacks measured cost or time · MiMo V2.6 Pro — Infinite cathedral corridor shader lacks measured cost or time · MiMo V2.6 Pro — Neo-gothic storm city shader lacks measured cost or time · MiMo V2.6 Pro — Sekiro Main Menu lacks measured cost or time · DeepSeek V4 Pro — Neo-gothic storm city shader lacks measured cost or time · Qwen3.8 Max — Campfire under the stars Non-USD cost; excluded from USD averages and the cost × time plot. · Qwen3.8 Max — Explorable space-flight game Non-USD cost; excluded from USD averages and the cost × time plot. · Qwen3.8 Max — Fighter Game v1 Non-USD cost; excluded from USD averages and the cost × time plot. · Qwen3.8 Max — Infinite cathedral corridor shader Non-USD cost; excluded from USD averages and the cost × time plot. · Qwen3.8 Max — JRPG boss battle Non-USD cost; excluded from USD averages and the cost × time plot. · Qwen3.8 Max — Red Sands v1 Non-USD cost; excluded from USD averages and the cost × time plot. · Qwen3.8 Max — Space Flight Stage 2 — Landfall Non-USD cost; excluded from USD averages and the cost × time plot. · Jev 1.13 — Apple Carry lacks measured cost or time · Jev 1.13 — Apple Carry lacks measured cost or time · GPT-6 Astra (low) planner + Jev 1.13 actor — Apple Carry lacks measured cost or time · GPT-6 Astra (low) planner + Jev 1.13 actor — Apple Stem lacks measured cost or time · GPT-6 Astra (low) planner + Jev 1.13 actor — Dex Cube Turn lacks measured cost or time · GPT-6 Astra (low) planner + Jev 1.13 actor — Eiffel Tower Drawing lacks measured cost or time · Laya 421M — Apple Carry lacks measured cost or time · Laya 421M — Apple Carry lacks measured cost or time · SemIf + Qwen3.5-4B — Apple Carry lacks measured cost or time · SemIf + Qwen3.5-4B — Apple Carry lacks measured cost or time · GPT-6 Astra planner + Jev 1.13 — Dex Cube — 3 Move lacks measured cost or time · GPT-6 Astra planner/author + Jev 1.13 actor — Apple Stem lacks measured cost or time · SemIf + Qwen3-0.6B — Apple Carry lacks measured cost or time