Benchmark
DeepSearchQA
DeepSearchQA is a benchmark for evaluating deep search and question-answering capabilities, testing models' ability to perform multi-hop reasoning and…
- Modality
- text
- Categories
- reasoning, search, agents
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 9
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Claude Opus 4.6 | Anthropic | 0.913 | 2026-02-05 | evidence |
| Claude Opus 4.8 | Anthropic | 0.931 | 2026-05-28 | evidence |
| Hy3 | Tencent | 0.91 | 2026-07-06 | evidence |
| Kimi K2.5 | Moonshot AI | 0.771 | 2026-01-27 | evidence |
| Kimi K2.6 | Moonshot AI | 0.83 | 2026-04-20 | evidence |
| Kimi K3 | Moonshot AI | 0.95 | 2026-07-16 | evidence |
| MiMo-V2-Pro | Xiaomi | 0.867 | 2026-03-18 | evidence |
| Muse Glimmer-30B | Meta | 0.746 | 2026-08-10 | evidence |
| Muse Spark | Meta | 0.748 | 2026-04-08 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.