Compare models
Up to five models, tasks down the page. A cell is passes / judged runs for that task. N/A means that model has no run there.
Select models (max 5) · 1 of 5
| Task | Claude Sonnet 5.55/6 judgedAnthropic Claude Code |
|---|---|
| All judged runspasses / judged runs | 83.3%5/6 passes / judged runs |
| Apple CarryCarry an apple onto a plate on the FR3 with a Robotiq 2F-85. | 100%1/1 passes / judged runs |
| Apple StemPinch an apple by the stem and lift it with a Wuji hand on an FR3 arm in SuperDex, without contacting the apple body. | 100%1/1 passes / judged runs |
| ATS Depot DrivingLeave the ATS depot, join a public road, negotiate the first junction, and stop safely. | unjudged |
| Bluetooth Speaker PCBDesign a Bluetooth speaker printed circuit board in tscircuit from the pinned task. | unjudged |
| CAD-002 Robot ArmBuild the CAD-002 v1.0.1 robot-arm fixture. | unjudged |
| CARVEBuild a playable Babylon.js WebGPU snowboarding game with the supplied rider asset, carved terrain, tricks, obstacles, audio, and a compl… | unjudged |
| Claw UnlockFind a collision-free rigid motion that unlocks two interlocked wire claws using pure geometry. | 0%0/1 passes / judged runs |
| Courtyard Blossom Stage 2Build the cherry-blossom temple courtyard arena in Blender through the pinned reference-exposed task. | unjudged |
| Dex Cube — 3 MoveComplete the three-move Rubik's cube sequence D, F', U2 with regrasp, using two dexterous hands in MuJoCo. | 100%1/1 passes / judged runs |
| Dex Cube TurnTurn one face of a Rubik's cube a quarter turn by finger contact with two dexterous hands in MuJoCo. | 100%1/1 passes / judged runs |
| Eiffel Tower DrawingDraw the Eiffel Tower with a friction-held pencil on a Marvin arm and Wuji hand in MuJoCo. | 100%1/1 passes / judged runs |
| Explorable space-flight gameBuild the browser space-flight game through stage-2 landfall. | unjudged |
| High-voxel-density Jungle Temple dioramaCreate a complete inspectable Blender voxel diorama of a jungle temple at a fixed 0.05-unit voxel resolution through the Blender MCP work… | unjudged |
| High-voxel-density Oasis Outpost dioramaCreate a complete inspectable Blender voxel diorama of an oasis outpost at a fixed 0.05-unit voxel resolution through the Blender MCP wor… | unjudged |
| Infinite cathedral corridor shaderGenerate an infinite stained-glass cathedral corridor shader with convincing depth, architectural repetition, light, and motion. | unjudged |
| JRPG boss battleBuild an interactive Three.js JRPG boss battle with supplied character assets, required combat beats, animation, sound controls, effects,… | unjudged |
| Neo-gothic storm city shaderGenerate a TWIGL-style neo-gothic storm city shader with legible atmosphere, architecture, lighting, water, and motion. | unjudged |
| Neon GunnerBuild a playable destructible neon run-and-gun game in the browser under the pinned Harness task contract. | unjudged |
| Sekiro Main MenuRecreate a high-end cinematic Sekiro-style main menu in the browser from the pinned reference and task contract. | unjudged |
| Space Flight Stage 2 — LandfallBuild the browser space-flight game through stage-2 landfall. | unjudged |
| Turbofan EngineCreate the CAD-001 v1.0.1 turbofan submission in the native CAD workflow. | unjudged |
The stronger green cell is the best pass rate in that row. Ties share it. Unjudged runs are left out of the rate.