Deep research on HLE
51AccuracyKimi-K2-Thinking-1T
Evaluation Results
| Method | Links | |
|---|---|---|
| Kimi-K2-Thinking-1TModel Category=Large Open-Source Models, Model Size=> 70B2026.02 | 51 | |
| GLM-4.7-358BModel Category=Large Open-Source Models, Model Size=> 70B2026.02 | 42.8 | |
| GPT-5-highModel Category=Closed-Source Models2026.02 | 42 | |
| DeepSeek-V3.2-Thinking-685BModel Category=Large Open-Source Models, Model Size=> 70B2026.02 | 40.8 | |
| Gemini-3-proModel Category=Closed-Source Models2026.02 | 38.3 | |
| Tongyi-DeepResearch-30B-A3BModel Category=Intermediate-sized Open-Source Models, Model Size=15B~70B2026.02 | 32.9 | |
| Claude-4.5-SonnetModel Category=Closed-Source Models2026.02 | 32 | |
| MiniMax-M2-229BModel Category=Large Open-Source Models, Model Size=> 70B2026.02 | 31.8 | |
| RE-TRAC-30B-A3BModel Category=Intermediate-sized Open-Source Models, Model Size=15B~70B2026.02 | 31.5 | |
| WebSailor-V2-30B-A3B (RL)Model Category=Intermediate-sized Open-Source Models, Model Size=15B~70B2026.02 | 30.6 | |
| IterResearch-30B-A3BModel Category=Intermediate-sized Open-Source Models, Model Size=15B~70B2026.02 | 28.8 | |
| OpenAI DeepResearchModel Category=Closed-Source Models2026.02 | 26.6 | |
| o3Model Category=Closed-Source Models2026.02 | 24.9 | |
| RE-TRAC-4BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 22.2 | |
| AgentCPM-Explore-4BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 19.1 | |
| WebExplorer-8BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 17.3 |