BAGEL - Wikipedia Communication: leaderboard

BAGEL Wikipedia questions on how a species communicates, including vocalization. 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 234 Wikipedia communication 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 4.689.7#113
2GPT-5.485#135
3Qwen 3 32BNon-reasoning77.4#972
4Gemma 3 27B (IT)76.5#1324
5Phi-475.2#1931
6Qwen 3 8BNon-reasoning73.1#1873
7Qwen 3 14BNon-reasoning71.8#1269
8Llama 3.1 8B Instruct69.2#4600
9Mistral 7B Instruct (v0.3)67.9#6750
10Qwen 3 4BNon-reasoning65#2348
11gemma-7B53.8#7121
12Qwen 3 0.6BNon-reasoning23.9#8350
13SmolLM2-360M21.8#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-communication · How It Works · Data refreshed daily, snapshot 2026-11-21.