CresOWLve - Exact Match: leaderboard

Creative problem-solving on CresOWLve (2026), 2,061 expert-written puzzles from the quiz game What? Where? When?, each needing several real-world facts from different domains joined by a non-obvious creative connection, answered zero-shot in the English version. Exact-match accuracy after lowercasing and punctuation removal, in percent; higher is better.

Metric: Exact-match accuracy (%) after lowercasing and punctuation removal, English version, on the 2,061 creative questions of CresOWLve (expert-written What? Where? When? puzzles that need several real-world facts joined by a creative leap), zero-shot; non-thinking models with chain-of-thought prompting, thinking models at the stated effort; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 14 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3.1 Pro (Preview)51.29#99
2Gemini 3 FlashMedium35.08#175
3Qwen 3.5 397B A17B19.36#264
4GLM-518.92#269
5GPT-5.4Medium17.81#135
6DeepSeek V3.2Thinking15.33#419
7Qwen 3 235B A22B 2507 (Thinking)13.49#466
8GPT-4.113.44#505
9Qwen 3 235B A22B 2507 Instruct13.05#616
10Mistral Large 311.26#832
11GPT-4.1 Mini7.33#789
12Llama 3.3 70B Instruct5.05#1385
13Command A4.46#1296
14OLMo-2-0325-32B-Instruct2.09#2841

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=cresowlve-exact-match · How It Works · Data refreshed daily, snapshot 2026-11-21.