Deep Research on DeepResearch Bench (test)
56.28ComprehensivenessVeriTrace
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| VeriTraceConfig=DeepSeek2026.05 | 56.28 | 59.56 | 52.24 | 51.98 | 55.77 | 235.66 | 73.28 | |
| FS-ResearcherBackbone=Claude-Sonnet-4.52026.05 | 54.25 | 55.85 | 52.47 | 51.54 | 53.94 | 139.91 | 76.17 | |
| VeriTraceConfig=Plus2026.05 | 52.84 | 57.08 | 51.65 | 49.61 | 53.5 | — | — | |
| WebWeaverBackbone=Qwen3-235B-A22B-Instruct-25072026.05 | 51.29 | 51 | 49.98 | 48.89 | 50.62 | 166.73 | 78.25 | |
| VeriTraceConfig=3B2026.05 | 50.85 | 55.22 | 50.38 | 49.08 | 51.96 | — | — | |
| VeriTraceConfig=27B, Backbone=Qwen3.5-27B2026.05 | 50.84 | 55.86 | 50.72 | 49.29 | 52.28 | 134.2 | 68.46 | |
| RhinoInsightBackbone=Gemini-2.5-Pro2026.05 | 50.51 | 51.45 | 51.72 | 50 | 50.92 | — | — | |
| LangChain-Open-Deep-ResearchBackbone=GPT-5, Provider=LangChain, Inc.2026.05 | 50.06 | 50.76 | 51.31 | 49.72 | 50.6 | 22.44 | 34.74 | |
| EnterpriseDRBackbone=Gemini-2.5-Pro2026.05 | 49.7 | 51.24 | 50.52 | 50.61 | 50.62 | — | 72.5 | |
| Gemini-2.5-Pro-DRProvider=Google2026.05 | 49.51 | 49.45 | 50.12 | 50 | 49.71 | 165.34 | 78.3 | |
| OpenAI-DRProvider=OpenAI2026.05 | 46.46 | 43.73 | 49.39 | 47.22 | 46.45 | 39.79 | 75.01 | |
| Claude-DeepResearchProvider=Anthropic2026.05 | 45.34 | 42.79 | 47.58 | 44.66 | 45 | — | — | |
| Kimi-ResearcherProvider=Moonshot AI2026.05 | 44.96 | 41.97 | 47.14 | 45.59 | 44.64 | — | — | |
| Doubao-DeepResearchProvider=ByteDance2026.05 | 44.84 | 40.56 | 47.95 | 44.69 | 44.34 | 52.62 | 52.86 |