CresOWLve - Russian 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 original Russian. Exact-match accuracy after lowercasing, punctuation removal and Unicode normalization, in percent; higher is better.

Metric: Exact-match accuracy (%) after lowercasing, punctuation removal and Unicode normalization, original Russian 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)67.78#99
2Gemini 3 FlashMedium51.82#175
3GLM-528.87#269
4GPT-5.4Medium26.88#135
5Qwen 3.5 397B A17B26.15#264
6GPT-4.117.03#505
7Mistral Large 315.48#832
8Qwen 3 235B A22B 2507 Instruct13.54#616
9Qwen 3 235B A22B 2507 (Thinking)13.34#466
10DeepSeek V3.2Thinking10.48#419
11GPT-4.1 Mini4.85#789
12Command A3.74#1296
13Llama 3.3 70B Instruct3.64#1385
14OLMo-2-0325-32B-Instruct0.44#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-russian-exact-match · How It Works · Data refreshed daily, snapshot 2026-11-21.