DeepSearchQA — Deep-search QA agentic benchmark, accuracy metric; distinct from f1-metric variant
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Kimi K2.6 | Moonshot | 83 | 1 | 2026-05-03 |
| 2 | Claude Opus 4.6 | Anthropic | 80.6 | 1 | 2026-05-03 |
| 3 | Kimi K2.5 | Moonshot | 77.1 | 1 | 2026-05-03 |
| 4 | GPT-5.4 | OpenAI | 63.7 | 1 | 2026-05-03 |
| 5 | Gemini 3.1 Pro | 60.2 | 2 | 2026-05-03 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.