DeepSearchQA (F1 score)
Search · 2026-01-28
DeepSearchQA F1 scores exhaustive answer lists for 900 multi-step web information-seeking prompts across 17 fields, balancing precision and recall.
Top models (higher is better)
| Model | Score |
|---|---|
| Atria Dawn Preview | 96.0 |
| Claude Opus 5 | 95.0 |
| Kimi K3 | 95.0 |
| Claude Fable 5 | 94.4 |
| Claude Mythos Preview | 94.4 |
| Opus 4.8 | 93.1 |
| Opus 4.6 | 91.3 |
| Sonnet 4.6 | 89.2 |
| Opus 4.7 | 89.1 |
| Beam 1.0 501B A23B | 80.5 |
| GPT-5 Pro | 79.0 |
| Gemini 3 Pro Preview | 76.9 |
| GPT-5 | 73.2 |
| o3-deep-research | 66.5 |
| o4-mini-deep-research (2025-06-26) | 61.8 |
| Gemini 2.5 Flash | 43.0 |
| Opus 4.5 | 40.2 |
| Sonnet 4.5 | 27.9 |
| Haiku 4.5 | 22.2 |