Information Retrieval on BrowseComp+ (BC+)
61.9RecallOpus-4.6
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Opus-4.6Category=Frontier models2026.06 | 61.9 | 73.6 | 63.4 | |
| Kimi-K2.5Category=Frontier models2026.06 | 59.3 | 67 | 73.9 | |
| Harness-1Parameters=20B, Category=Open-source small models2026.06 | 58.4 | 66.7 | 66.5 | |
| GPT-OSSParameters=120B, Category=Frontier models2026.06 | 50.8 | 64.1 | 68.2 | |
| Sonnet-4.6Category=Frontier models2026.06 | 50.5 | 59.7 | 53.5 | |
| Context-1Parameters=20B, Category=Open-source small models2026.06 | 50 | 61.8 | 56.7 | |
| GPT-5.4Category=Frontier models2026.06 | 44.3 | 49.9 | 47.6 | |
| Tongyi DeepResearchParameters=30B, Category=Open-source small models2026.06 | 38.1 | 42.8 | 41.3 | |
| GPT-OSSParameters=20B, Category=Open-source small models2026.06 | 10.9 | 15.6 | 24.6 | |
| Qwen3Parameters=32B, Category=Open-source small models2026.06 | 7.2 | 9.2 | 15.4 | |
| Search-R1Parameters=32B, Category=Open-source small models2026.06 | 5.3 | 7.4 | 5.3 |