List your company

File Understanding and Generation on GAIA File

79ScoreClaude-4.6-Sonnet-Thinking
22.00836.80451.666.396Jun 13, 2026

Evaluation results

MethodLinks
Claude-4.6-Sonnet-ThinkingSize=-, Train=-2026.0679
Gemini-3.1-Pro-PreviewSize=-, Train=-2026.0677.4
Doubao-2.0-ProSize=-, Train=-2026.0671
GLM-5Size=744B, Train=-2026.0670.7
MiniMax-M2.7Size=230B, Train=-2026.0669.4
Qwen3.5-397BSize=397B, Train=-2026.0667.7
Kimi-K2.5Size=1T, Train=-2026.0667.7
GPT-5.2Size=-, Train=-2026.0662.9
DeepSeek-V3.2Size=671B, Train=-2026.0662.9
S1-DeepResearchSize=32B, Train=SFT2026.0662.9
Qwen3-235BSize=235B, Train=-2026.0640.3
Qwen3-32BSize=32B, Train=-2026.0624.2