Encyclo-K - History: leaderboard
Encyclo-K's multi-statement selection questions restricted to History: accuracy over the 686 History questions of the 5,038-question standard set.
Metric: Accuracy on the 686 History questions (%). Source: encyclo-k.github.io. Saturation forecast: Around October 2027. 37 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3 235B A22B 2507 (Thinking) | 45.19 | #469 | |
| 2 | DeepSeek V3.1 Terminus | Thinking | 45.04 | #440 |
| 3 | Qwen 3 235B A22B 2507 Instruct | 43.59 | #618 | |
| 4 | Kimi K2 0905 | 40.96 | #564 | |
| 5 | Qwen 3 235B A22B | Thinking | 37.9 | #631 |
| 6 | Qwen 3 30B A3B 2507 (Thinking) | 34.99 | #765 | |
| 7 | QwQ-32B | 34.84 | #908 | |
| 8 | Qwen 3 32B | Thinking | 32.65 | #965 |
| 9 | Qwen 3 30B A3B 2507 Instruct | 32.51 | #1091 | |
| 10 | DeepSeek V3 (0324) | 29.88 | #722 | |
| 11 | Qwen 3 30B A3B | Thinking | 28.43 | #1155 |
| 12 | Qwen 3 14B | Reasoning | 26.68 | #1264 |
| 13 | Qwen 2.5 32B Instruct | 25.22 | #1257 | |
| 14 | Qwen 3 8B | Thinking | 25.22 | #1868 |
| 15 | Qwen 3 4B 2507 Instruct | 24.93 | #2215 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=encyclo-k-history · How It Works · Data refreshed daily, snapshot 2026-11-17.