Deep Research on xbench
83AccuracyRE-TRAC-30B-A3B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RE-TRAC-30B-A3BModel Category=Intermediate-sized Open-Source Models, Model Size=15B~70B2026.02 | 83 | — | |
| GPT-5-highModel Category=Closed-Source Models2026.02 | 77.9 | — | |
| RE-TRAC-4BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 76.6 | — | |
| Tongyi-DeepResearch-30B-A3BModel Category=Intermediate-sized Open-Source Models, Model Size=15B~70B2026.02 | 75 | — | |
| NestBrowse-4BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 74 | — | |
| WebSailor-V2-30B-A3B (RL)Model Category=Intermediate-sized Open-Source Models, Model Size=15B~70B2026.02 | 73.7 | — | |
| MiniMax-M2-229BModel Category=Large Open-Source Models, Model Size=> 70B2026.02 | 72 | — | |
| AgentCPM-Explore-4BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 70 | — | |
| o3Model Category=Closed-Source Models2026.02 | 66.7 | — | |
| Claude-4.5-SonnetModel Category=Closed-Source Models2026.02 | 66 | — | |
| WebExplorer-8BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 53.7 | — | |
| InfoAgent-14BModel Category=Compact Open-Source Models, Model Size=< 15B2026.02 | 40.4 | — | |
| Youtu-LLM 2BThinking Mode=true, ReAct Framework=true, LLM-as-a-Judge=true2025.12 | 19.5 | 19.5 | |
| Qwen3 4BThinking Mode=true, ReAct Framework=true, LLM-as-a-Judge=true2025.12 | 18.4 | 18.4 | |
| Co-SightBase Model=Qwen3-14B2026.02 | 16 | — | |
| TOOLSELFBase Model=Qwen3-14B2026.02 | 16 | — | |
| WebSailorBase Model=Qwen3-14B2026.02 | 15 | — | |
| SmolLM3 3BThinking Mode=true, ReAct Framework=true, LLM-as-a-Judge=true2025.12 | 13.9 | 13.9 | |
| Vanilla AgentBase Model=Qwen3-14B2026.02 | 13 | — | |
| Co-SightBase Model=Qwen3-8B2026.02 | 13 | — | |
| OAgentsBase Model=Qwen3-14B2026.02 | 12 | — | |
| OWLBase Model=Qwen3-14B2026.02 | 12 | — | |
| Qwen3 1.7BThinking Mode=true, ReAct Framework=true, LLM-as-a-Judge=true2025.12 | 11.7 | 11.7 | |
| ReSumBase Model=Qwen3-14B2026.02 | 11 | — | |
| TOOLSELFBase Model=Qwen3-8B2026.02 | 10 | — | |
| OAgentsBase Model=Qwen3-8B2026.02 | 9 | — | |
| ReSumBase Model=Qwen3-8B2026.02 | 7 | — | |
| OWLBase Model=Qwen3-8B2026.02 | 7 | — | |
| Vanilla AgentBase Model=Qwen3-8B2026.02 | 6 | — | |
| WebSailorBase Model=Qwen3-8B2026.02 | 4 | — |