List your company

Physical Reasoning on Pooltool

36.5Att. 1 ScoreGemini-2.5-Pro
-1.468.39518.2528.105Mar 1, 2026

Evaluation results

MethodLinks
Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=-2026.0336.568
Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=Gemini-2.5-Pro2026.032560
Qwen-7BPolicy Model=Qwen-7B, World Model=-2026.0323.526.5
MOCKPolicy Model=MOCK, World Model=-2026.032.3348
Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=-2026.03266
Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=Qwen-7B^P2026.03267.33
Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=-2026.03267
Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=Qwen-7B^P&I2026.03269
Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=-2026.03164
Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=Qwen-7B^I2026.03166.67
Qwen-3BPolicy Model=Qwen-3B, World Model=-2026.03050
Qwen-32BPolicy Model=Qwen-32B, World Model=-2026.03014.29
Qwen-72BPolicy Model=Qwen-72B, World Model=-2026.03018
Qwen-72BPolicy Model=Qwen-72B, World Model=Qwen-72B2026.03014
Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=-2026.03049
Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=Claude 4.0 Opus2026.03042
GPT-o3Policy Model=GPT-o3, World Model=-2026.03025.67
GPT-o3Policy Model=GPT-o3, World Model=GPT-o32026.03022
Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=-2026.03051
Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=Qwen-3B^P2026.03053.67
Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=-2026.03043
Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=Qwen-3B^I2026.03045.33
Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=-2026.03057
Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=Qwen-3B^P&I2026.03059.67
Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=-2026.03058
Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=Qwen-3B^P2026.03061
Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=-2026.03050
Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=Qwen-3B^I2026.03052.33
Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=-2026.03055
Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=Qwen-3B^P&I2026.03057.33
Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=-2026.03066
Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=Qwen-7B^P2026.03069
Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=-2026.03060
Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=Qwen-7B^I2026.03063
Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=-2026.03069
Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=Qwen-7B^P&I2026.03071