Deep research on GAIA
78.2AccuracyRE-TRAC-30B-A3B
Evaluation Results
| Method | Links | |
|---|---|---|
| RE-TRAC-30B-A3BModel Category=Intermediate-sized Open-Source Models, Model Size=15B~70B2026.02 | 78.2 | |
| GPT-5-highModel Category=Closed-Source Models2026.02 | 76.7 | |
| MiniMax-M2-229BModel Category=Large Open-Source Models, Model Size=> 70B2026.02 | 75.7 | |
| Gemini-3-proModel Category=Closed-Source Models2026.02 | 74.8 | |
| WebSailor-V2-30B-A3B (RL)Model Category=Intermediate-sized Open-Source Models, Model Size=15B~70B2026.02 | 74.1 | |
| IterResearch-30B-A3BModel Category=Intermediate-sized Open-Source Models, Model Size=15B~70B2026.02 | 72.8 | |
| Claude-4.5-SonnetModel Category=Closed-Source Models2026.02 | 71.2 | |
| Tongyi-DeepResearch-30B-A3BModel Category=Intermediate-sized Open-Source Models, Model Size=15B~70B2026.02 | 70.9 | |
| o3Model Category=Closed-Source Models2026.02 | 70.5 | |
| RE-TRAC-4BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 70.4 | |
| NestBrowse-4BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 68.9 | |
| OpenAI DeepResearchModel Category=Closed-Source Models2026.02 | 67.4 | |
| OPENRESEARCHER2026.03 | 64.1 | |
| AgentCPM-Explore-4BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 63.9 | |
| Kimi-K2type=Foundation Models with Tools2026.03 | 57.7 | |
| Claude-4-Sonnettype=Foundation Models with Tools2026.03 | 57.6 | |
| OpenAI o4-minitype=Foundation Models with Tools2026.03 | 55.8 | |
| WebSailor-72Btype=Deep Research Agents2026.03 | 55.4 | |
| DeepMiner-32Btype=Deep Research Agents2026.03 | 54.4 | |
| ASearcher-QwQ-32Btype=Deep Research Agents2026.03 | 52.8 | |
| WebDancer-QwQ-32Btype=Deep Research Agents2026.03 | 51.5 | |
| Nemotron-3-Nanotype=Foundation Models with Tools2026.03 | 50.5 | |
| WebExplorer-8BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 50 | |
| DeepSeek-R1type=Foundation Models with Tools2026.03 | 30.3 |