General AI Assistant Task Completion on GAIA Text-Only
0.874AccuracySeed-1.8
Evaluation Results
| Method | Links | |
|---|---|---|
| Seed-1.8Model Access Type=Closed-Source2026.02 | 0.874 | |
| OpenAI-GPT-5-highModel Access Type=Closed-Source2026.02 | 0.764 | |
| Minimax-M2Model Access Type=Closed-Source2026.02 | 0.757 | |
| WebSailor-V2-30B-A3BModel Access Type=Open-Source2026.02 | 0.741 | |
| WebLeaper-30B-A3BModel Access Type=Open-Source2026.02 | 0.732 | |
| IterResearch-30B-A3BModel Access Type=Open-Source2026.02 | 0.728 | |
| GLM-4.6Model Access Type=Closed-Source2026.02 | 0.719 | |
| Claude-4.5-SonnetModel Access Type=Closed-Source2026.02 | 0.712 | |
| Tongyi-DeepResearch 30BModel Access Type=Open-Source2026.02 | 0.709 | |
| MiroThinker 8BModel Access Type=Open-Source2026.02 | 0.664 | |
| AgentCPM-Explore-4BModel Access Type=Open-Source2026.02 | 0.639 | |
| DeepSeek-V3.2Model Access Type=Closed-Source2026.02 | 0.635 | |
| Merged-Model-4BModel Access Type=Open-Source2026.02 | 0.601 | |
| ASearcher-QWQ-32B v2Model Access Type=Open-Source2026.02 | 0.587 | |
| WebDancer-QwQ-32BModel Access Type=Open-Source2026.02 | 0.515 |