Encyclo-K - Philosophy: leaderboard

Encyclo-K's multi-statement selection questions restricted to Philosophy: accuracy over the 61 Philosophy questions of the 5,038-question standard set.

Metric: Accuracy on the 61 Philosophy 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 Instruct72.13#618
2DeepSeek V3.1 TerminusThinking68.85#440
3Qwen 3 235B A22B 2507 (Thinking)60.66#469
4Kimi K2 090557.38#564
5Qwen 3 235B A22BThinking57.38#631
6QwQ-32B54.1#908
7Qwen 3 30B A3B 2507 (Thinking)52.46#765
8Qwen 3 30B A3B 2507 Instruct49.18#1091
9Qwen 3 32BThinking47.54#965
10Qwen 3 4B 2507 Instruct40.98#2215
11DeepSeek V3 (0324)36.07#722
12Qwen 2.5 32B Instruct34.43#1257
13Qwen 3 14BReasoning34.43#1264
14Qwen 3 30B A3BNon-reasoning31.15#1155
15Qwen 3 8BThinking26.23#1868

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-philosophy · How It Works · Data refreshed daily, snapshot 2026-11-17.