List your company

Physical Reasoning on Cut the Rope

26.14Success RateClaude 4.0 Opus
6.047211.263616.4821.6964Mar 1, 2026

Evaluation results

MethodLinks
Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=-2026.0326.14
Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=Claude 4.0 Opus2026.0323.86
Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=-2026.0322.73
Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=Qwen-7B^P&I2026.0321.2
Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=Gemini-2.5-Pro2026.0320.45
Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=Qwen-7B^P&I2026.0319.33
Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=Qwen-7B^P2026.0318.88
GPT-o3Policy Model=GPT-o3, World Model=-2026.0318.18
Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=Qwen-7B^P2026.0317.5
Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=-2026.0317.05
Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=-2026.0316.55
GPT-o3Policy Model=GPT-o3, World Model=GPT-o32026.0316.5
Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=-2026.0316.1
Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=Qwen-3B^P&I2026.0315.8
Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=-2026.0315.35
Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=Qwen-3B^P&I2026.0314.05
Qwen-72BPolicy Model=Qwen-72B, World Model=-2026.0313.64
Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=Qwen-3B^P2026.0312.98
Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=-2026.0312.1
Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=Qwen-3B^P2026.0311.85
Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=-2026.0311.6
Qwen-72BPolicy Model=Qwen-72B, World Model=Qwen-72B2026.0311.5
MOCKPolicy Model=MOCK, World Model=-2026.0311.36
Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=-2026.0311.05
Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=Qwen-7B^I2026.0310.36
Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=-2026.0310.23
Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=Qwen-7B^I2026.0310.15
Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=Qwen-3B^I2026.039.88
Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=Qwen-3B^I2026.039.13
Qwen-7BPolicy Model=Qwen-7B, World Model=-2026.039.09
Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=-2026.038.21
Qwen-3BPolicy Model=Qwen-3B, World Model=-2026.037.95
Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=-2026.037.95
Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=-2026.037.8
Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=-2026.037.75
Qwen-32BPolicy Model=Qwen-32B, World Model=-2026.036.82