BAGEL - Wikipedia Behavior: leaderboard

BAGEL Wikipedia questions on animal behavior, including social behavior. Four-option closed-book questions written by GPT-4o-mini from source material that is withheld at test time; accuracy in percent, higher is better.

Metric: Accuracy (%, times 100) on the 353 Wikipedia behavior questions of BAGEL, closed-book four-option single-answer multiple choice (the source passage is withheld), one unified prompt, greedy decoding with seed 0, a single run per model; questions written by GPT-4o-mini from Wikipedia species articles, GloBI interaction records, bioRxiv preprints and Xeno-canto recordings, options shuffled; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Opus 4.687#113
2GPT-5.481.9#135
3Qwen 3 32BNon-reasoning74.2#972
4Phi-473.7#1931
5Qwen 3 8BNon-reasoning72.2#1873
6Qwen 3 14BNon-reasoning72.2#1269
7Gemma 3 27B (IT)70#1324
8Llama 3.1 8B Instruct67.7#4600
9Qwen 3 4BNon-reasoning63.5#2348
10Mistral 7B Instruct (v0.3)60.6#6750
11gemma-7B52.4#7121
12Qwen 3 0.6BNon-reasoning24.6#8350
13SmolLM2-360M22.7#9570

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

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