Encyclo-K - Education: leaderboard

Encyclo-K's multi-statement selection questions restricted to Education: accuracy over the 109 Education questions of the 5,038-question standard set.

Metric: Accuracy on the 109 Education questions (%). Source: encyclo-k.github.io. Saturation forecast: Around February 2027. 37 models tracked. Updated 17 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Qwen 3 235B A22B 2507 (Thinking)61.47#469
2QwQ-32B60.55#908
3Qwen 3 235B A22B 2507 Instruct56.88#618
4DeepSeek V3.1 TerminusThinking55.05#440
5Kimi K2 090549.54#564
6Qwen 3 235B A22BThinking49.54#631
7Qwen 3 30B A3B 2507 Instruct43.12#1091
8Qwen 3 32BThinking43.12#965
9Qwen 3 30B A3B 2507 (Thinking)43.12#765
10Qwen 3 8BThinking42.2#1868
11DeepSeek V3 (0324)38.53#722
12Qwen 3 30B A3BThinking38.53#1155
13Qwen 2.5 32B Instruct37.61#1257
14Qwen 3 14BReasoning37.61#1264
15Qwen 2.5 72B Instruct35.78#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-education · How It Works · Data refreshed daily, snapshot 2026-11-17.