Noometry

Reasoning benchmark

Thematic Generalization leaderboard

As of October 2026, Claude Opus 4.6 has the highest published Thematic Generalization score on Noometry at 80.6%, out of 23 models with results.

Last verified

About Thematic Generalization

Infer a narrow hidden theme from a few examples and anti-examples, then pick the one candidate that fits it among close distractors.

Category
Reasoning
Introduced
2025
Format
Pick the example
Unit
Percent (random guessing ≈ 0%)
Official site
github.com

Top 15 models

  1. Claude Opus 4.6 80.6%
  2. GPT-5.4 80%
  3. Gemini 3.1 Pro Preview 79.4%
  4. Claude Sonnet 4.6 76.3%
  5. Claude Opus 4.7 72.8%
  6. GLM-5.1 69.8%
  7. Kimi K2.5 69.4%
  8. Qwen3.5 397B-A17B 65.1%
  9. DeepSeek-V3.2-Exp 65%
  10. Grok 4.20 (Non-Reasoning) 63.8%
  11. Gemini 3.1 Flash Lite 63.3%
  12. GPT-5.4 mini 61.7%
  13. Qwen3.6 Plus 59.5%
  14. Seed 2.0 Pro 57.1%
  15. Gemma 4 31B IT 53%

Sponsored placements are available on pages like this one. Advertise on Noometry

All results

#ModelProviderScoreSettingSourceDate
1Claude Opus 4.6 Anthropic80.6%high reasoningLech Mazur benchmarks
2GPT-5.4 OpenAI80%xhigh reasoningLech Mazur benchmarks
3Gemini 3.1 Pro Preview Google79.4%Lech Mazur benchmarks
4Claude Sonnet 4.6 Anthropic76.3%high reasoningLech Mazur benchmarks
5Claude Opus 4.7 Anthropic72.8%high reasoningLech Mazur benchmarks
6GLM-5.1 Z.ai (Zhipu)69.8%Lech Mazur benchmarks
7Kimi K2.5 Moonshot AI69.4%Lech Mazur benchmarks
8Qwen3.5 397B-A17B Alibaba (Qwen)65.1%Lech Mazur benchmarks
9DeepSeek-V3.2-Exp DeepSeek65%Lech Mazur benchmarks
10Grok 4.20 (Non-Reasoning) xAI63.8%reasoningLech Mazur benchmarks
11Gemini 3.1 Flash Lite Google63.3%Lech Mazur benchmarks
12GPT-5.4 mini OpenAI61.7%xhigh reasoningLech Mazur benchmarks
13Qwen3.6 Plus Alibaba (Qwen)59.5%Lech Mazur benchmarks
14Seed 2.0 Pro ByteDance Seed57.1%Lech Mazur benchmarks
15Gemma 4 31B IT Google53%Lech Mazur benchmarks
16Qwen3.5 122B-A10B Alibaba (Qwen)51.2%Lech Mazur benchmarks
17MiMo-V2-Pro Xiaomi45.9%Lech Mazur benchmarks
18Qwen3.5 27B Alibaba (Qwen)45.5%Lech Mazur benchmarks
19ERNIE 5.0 0110 Baidu41.7%Lech Mazur benchmarks
20Trinity Large Thinking Arcee AI41.6%Lech Mazur benchmarks
21MiniMax-M2.7 MiniMax39.3%Lech Mazur benchmarks
22Mistral Large 3 Mistral AI23%Lech Mazur benchmarks
23Mistral Medium 3.1 Mistral AI20.3%Lech Mazur benchmarks

Compare the leaders

Other reasoning benchmarks

Frequently asked questions

What does Thematic Generalization measure?

Infer a narrow hidden theme from a few examples and anti-examples, then pick the one candidate that fits it among close distractors.

Which model has the highest Thematic Generalization score?

As of October 2026, Claude Opus 4.6 has the highest published Thematic Generalization score on Noometry at 80.6%, out of 23 models with results.

What is the best open-weight model on Thematic Generalization?

GLM-5.1 has the highest Thematic Generalization accuracy among open-weight models at 69.8%, ranking 6 of 23 overall.