Encyclo-K - Economics: leaderboard

Encyclo-K's multi-statement selection questions restricted to Economics: accuracy over the 124 Economics questions of the 5,038-question standard set.

Metric: Accuracy on the 124 Economics questions (%). Source: encyclo-k.github.io. Saturation forecast: Around February 2027. 37 models tracked. Updated 17 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1DeepSeek V3.1 TerminusThinking57.26#440
2Qwen 3 235B A22B 2507 Instruct56.45#618
3Qwen 3 235B A22B 2507 (Thinking)55.65#469
4Kimi K2 090550#564
5Qwen 3 235B A22BThinking50#631
6QwQ-32B48.39#908
7Qwen 3 30B A3B 2507 (Thinking)40.32#765
8Qwen 3 32BThinking38.71#965
9Qwen 3 30B A3B 2507 Instruct33.06#1091
10Qwen 3 4B 2507 Instruct31.45#2215
11DeepSeek V3 (0324)29.84#722
12Qwen 3 30B A3BThinking29.03#1155
13Gemma 2 9B (IT)25#2351
14Qwen 3 8BThinking24.19#1868
15Qwen 2.5 72B Instruct23.39#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-economics · How It Works · Data refreshed daily, snapshot 2026-11-17.