List your company

File Understanding and Generation on GTA

77.9ScoreClaude-4.6-Sonnet-Thinking
46.49254.64662.870.954Jun 13, 2026

Evaluation results

MethodLinks
Claude-4.6-Sonnet-ThinkingSize=-, Train=-2026.0677.9
Doubao-2.0-ProSize=-, Train=-2026.0675
Gemini-3.1-Pro-PreviewSize=-, Train=-2026.0675
GPT-5.2Size=-, Train=-2026.0673.8
Qwen3.5-397BSize=397B, Train=-2026.0673.3
GLM-5Size=744B, Train=-2026.0672.7
MiniMax-M2.7Size=230B, Train=-2026.0672.1
Kimi-K2.5Size=1T, Train=-2026.0671.5
Qwen3-32BSize=32B, Train=-2026.0670.3
S1-DeepResearchSize=32B, Train=SFT2026.0668
Qwen3-235BSize=235B, Train=-2026.0665.7
DeepSeek-V3.2Size=671B, Train=-2026.0647.7