DrBencher - History: leaderboard
Metric: Answer accuracy (%) on the history domain questions on the 268 human-validated DrBencher questions (closed-book, default API temperature, mean of three runs, 2% relative tolerance and exact match for history); higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 30.6 |
| 2 | Llama 4 Maverick | 30.6 |
| 3 | Gemini 2.5 Flash | 24.7 |
| 4 | Qwen 3 30B A3B (Thinking) | 24.2 |
| 5 | GPT-5.2 | 22 |
| 6 | Mistral Small 3.2 | 18.3 |
Interactive version: theaggregate.ai/benchmark?slug=drbencher-history · How It Works · Data refreshed daily, snapshot 2026-10-07.