File Understanding and Generation on GTA
77.9ScoreClaude-4.6-Sonnet-Thinking
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude-4.6-Sonnet-ThinkingSize=-, Train=-2026.06 | 77.9 | |
| Doubao-2.0-ProSize=-, Train=-2026.06 | 75 | |
| Gemini-3.1-Pro-PreviewSize=-, Train=-2026.06 | 75 | |
| GPT-5.2Size=-, Train=-2026.06 | 73.8 | |
| Qwen3.5-397BSize=397B, Train=-2026.06 | 73.3 | |
| GLM-5Size=744B, Train=-2026.06 | 72.7 | |
| MiniMax-M2.7Size=230B, Train=-2026.06 | 72.1 | |
| Kimi-K2.5Size=1T, Train=-2026.06 | 71.5 | |
| Qwen3-32BSize=32B, Train=-2026.06 | 70.3 | |
| S1-DeepResearchSize=32B, Train=SFT2026.06 | 68 | |
| Qwen3-235BSize=235B, Train=-2026.06 | 65.7 | |
| DeepSeek-V3.2Size=671B, Train=-2026.06 | 47.7 |