DeepSearchQA: leaderboard
Deep-search question-answering benchmark for agents that must gather, compare, and synthesize evidence across multi-hop web research tasks.
Metric: Score (%). Source: arxiv.org. Source: llm-stats.com. Saturation forecast: Around March 2028. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3 | 95 | #30 |
| 2 | Claude Opus 4.8 | 93.1 | #37 |
| 3 | Claude Opus 4.6 | 91.3 | #63 |
| 4 | Hy3 | 91 | #93 |
| 5 | Muse Spark 1.3 | 89.4 | #24 |
| 6 | MiMo-V2-Pro | 86.7 | #168 |
| 7 | Kimi K2.6 | 83 | #104 |
| 8 | Kimi K2.5 | 77.1 | #144 |
| 9 | Muse Spark | 74.8 | #64 |
| 10 | Muse Glimmer 30B | 74.6 | #178 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=deepsearchqa · How It Works · Data refreshed daily, snapshot 2026-10-20.