DeepSearchQA
AI benchmark results and model performance
Type: percentageAgents
Recorded results
10
Average score
81.14%
Score range
67.70% - 95%
Leading model
95% - Kimi K3
Scores over time
Individual benchmark scores plotted by date.
Model results
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| Kimi K3 | 16 Jul 2026 | 95% | F1 score. | Yes | Source | |
| Claude Opus 4.6 | 05 Feb 2026 | 91.30% | - | Yes | Source | |
| MiMo V2 Pro | 18 Mar 2026 | 86.70% | - | Yes | Source | |
| MiMo V2 TTS (Free) | 18 Mar 2026 | 86.70% | inferred modality/version alias from mimo-v2-pro | Yes | Source | |
| Beam | 05 Oct 2026 | 80.10% | Reflection-reported launch score. Source row: DeepSearchQA w/context management. Accessed 2026-10-05T22:51:12.456Z. Harness, reasoning effort, sampling and trial count are not specified per row. Not independently reproduced. | Yes | Source | |
| Seed 2.0 Pro | 14 Feb 2026 | 77.40% | Seed2 official benchmark table | DeepSearchQA | Yes | Source | |
| Kimi K2.5 | 27 Jan 2026 | 77.10% | - | Yes | Source | |
| Muse Spark | 08 Apr 2026 | 74.80% | - | Yes | Source | |
| Muse Glimmer 30B | 10 Aug 2026 | 74.60% | High reasoning | Yes | Source | |
| Seed 2.0 Lite | 14 Feb 2026 | 67.70% | Seed2 official benchmark table | DeepSearchQA | Yes | Source |
