Agent on GAIA Text-Only
84.5ScoreSOTA with Equivalent Parameters
Evaluation Results
| Method | Links | |
|---|---|---|
| SOTA with Equivalent ParametersModel comparison=Equivalent Parameters2026.05 | 84.5 | |
| Kimi-K2.5Number of Parameters=1T-A32B2026.03 | 79.9 | |
| Intern-S1-ProNumber of Parameters=1T-A22B2026.03 | 77.4 | |
| Gemini-3-Pro2026.03 | 75.5 | |
| GPT-5.22026.03 | 71.1 | |
| JT-Safe-V2-35BParameters=35B2026.05 | 63.11 | |
| Qwen3-VL-235B-ThinkingNumber of Parameters=235B-A22B, Thinking Configuration=true2026.03 | 47.8 |