DrBencher - History: leaderboard
DrBencher (2026) generates questions that need multi-hop entity identification, property retrieval from authoritative sources and domain computation, built answer-first from knowledge-graph chains, and evaluates models closed-book on a human-validated set. This board is answer accuracy in percent on the history domain questions, the mean of three runs; higher is better.
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 2030. 6 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.6 | 30.6 | #113 | |
| 2 | Llama 4 Maverick | 30.6 | #1110 | |
| 3 | Gemini 2.5 Flash | 24.7 | #463 | |
| 4 | Qwen 3 30B A3B | Thinking | 24.2 | #1156 |
| 5 | GPT-5.2 | 22 | #185 | |
| 6 | Mistral Small 3.2 | 18.3 | #1641 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=drbencher-history · How It Works · Data refreshed daily, snapshot 2026-11-21.