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

TaskClaude Fable 5.14/4 judgedAnthropic Claude Code
All judged runspasses / judged runs100%4/4 passes / judged runs
Campfire under the starsBuild a polished interactive Three.js campfire scene under a starry night with convincing fire, lighting, environmental detail, and camer…unjudged
CARVEBuild a playable Babylon.js WebGPU snowboarding game with the supplied rider asset, carved terrain, tricks, obstacles, audio, and a compl…unjudged
Courtyard Blossom Stage 2Create a second cherry-blossom temple courtyard arena for the fixed fighting game under the pinned reference-guided Stage 2 contract.unjudged
ECHO Main MenuRecreate the pinned ECHO-style cinematic main menu reference as an interactive browser experience.unjudged
Explorable space-flight gameBuild a responsive browser space-flight game with flight controls, a coherent star-system environment, lighting, assets, and a playable g…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…100%1/1 passes / judged runs
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
High-voxel-density Shrine Village dioramaCreate a complete inspectable Blender voxel diorama of a shrine village at a fixed 0.05-unit voxel resolution through the Blender MCP wor…100%1/1 passes / judged runs
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
MacBook-class cinematic ad sceneCreate one polished MacBook-class product-ad shot in Blender with a modeled device, legible industrial detail, intentional materials, lig…100%1/1 passes / judged runs
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
Off-road Mud GameBuild a one-request procedural off-road driving game with vehicle physics, independent suspension, streamed terrain, mud feedback, and mu…100%1/1 passes / judged runs
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 — LandfallExtend the Stage 1 space-flight project with a seamless orbit-to-surface round trip, explorable terrain, takeoff, landing, and a fixed ch…unjudged
The Last of Us Main MenuRecreate the pinned The Last of Us-style main menu reference as an interactive browser experience.unjudged

The stronger green cell is the best pass rate in that row. Ties share it. Unjudged runs are left out of the rate.

RemakeBenchResearch console