Encyclo-K - Law: leaderboard
Encyclo-K's multi-statement selection questions restricted to Law: accuracy over the 189 Law questions of the 5,038-question standard set.
Metric: Accuracy on the 189 Law questions (%). Source: encyclo-k.github.io. Saturation forecast: Around May 2027. 37 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | DeepSeek V3.1 Terminus | Thinking | 52.38 | #440 |
| 2 | Qwen 3 235B A22B 2507 Instruct | 47.62 | #618 | |
| 3 | Qwen 3 235B A22B 2507 (Thinking) | 43.39 | #469 | |
| 4 | Qwen 3 235B A22B | Thinking | 40.21 | #631 |
| 5 | Kimi K2 0905 | 36.51 | #564 | |
| 6 | Qwen 3 30B A3B 2507 (Thinking) | 36.51 | #765 | |
| 7 | Qwen 3 30B A3B 2507 Instruct | 35.45 | #1091 | |
| 8 | QwQ-32B | 35.45 | #908 | |
| 9 | DeepSeek V3 (0324) | 32.8 | #722 | |
| 10 | Qwen 3 32B | Thinking | 31.22 | #965 |
| 11 | Qwen 3 14B | Reasoning | 28.04 | #1264 |
| 12 | Qwen 2.5 32B Instruct | 27.51 | #1257 | |
| 13 | Qwen 3 30B A3B | Thinking | 27.51 | #1155 |
| 14 | Qwen 3 4B 2507 Instruct | 25.93 | #2215 | |
| 15 | Qwen 2.5 72B Instruct | 25.4 | #1119 |
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-law · How It Works · Data refreshed daily, snapshot 2026-11-17.