Encyclo-K - Management: leaderboard

Encyclo-K's multi-statement selection questions restricted to Management: accuracy over the 73 Management questions of the 5,038-question standard set.

Metric: Accuracy on the 73 Management 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)47.95#469
2Qwen 3 235B A22BThinking45.21#631
3Qwen 3 235B A22B 2507 Instruct43.84#618
4DeepSeek V3.1 TerminusThinking42.47#440
5Qwen 3 30B A3B 2507 Instruct39.73#1091
6Kimi K2 090539.73#564
7Qwen 3 32BThinking38.36#965
8QwQ-32B34.25#908
9Qwen 3 4B 2507 Instruct31.51#2215
10Qwen 3 30B A3B 2507 (Thinking)31.51#765
11Qwen 3 8BThinking28.77#1868
12Qwen 3 14BReasoning28.77#1264
13DeepSeek V3 (0324)27.4#722
14Qwen 2.5 72B Instruct24.66#1119
15Gemma 2 9B (IT)24.66#2351

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