Benchmark
DeepSearchQA Benchmark
What is DeepSearchQA?
Live-web deep research; F1 grading depends on the reference answer set. Benchmark Radar tracks 1 reported scores for DeepSearchQA, cited by 2 source documents.
- Released
- 2026-02-10
- Evaluates
- agent
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 1
Source provenance
- Original evidence https://huggingface.co/datasets/PokeeAI/DeepSearchQA
DeepSearchQA links
DeepSearchQA results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Kimi K3 | Moonshot AI | 95.0 | 2026-06-13 | 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.
Which sources cite DeepSearchQA?
- Claude Opus 5 Anthropic, 2026-07-24
- Kimi K3 Moonshot AI, 2026-06-13