BAGEL - Xeno-canto Call Duration: leaderboard

BAGEL Xeno-canto questions on typical call or syllable duration, answered from text alone. 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 649 Xeno-canto questions on call or syllable duration 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 2033. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-5.443.9#135
2Claude Opus 4.643.5#113
3Qwen 3 14BNon-reasoning42.1#1269
4Qwen 3 4BNon-reasoning34.2#2348
5Mistral 7B Instruct (v0.3)32.7#6750
6Llama 3.1 8B Instruct32.5#4600
7Qwen 3 8BNon-reasoning32.2#1873
8gemma-7B31.4#7121
9Phi-430.8#1931
10Qwen 3 32BNon-reasoning29#972
11Qwen 3 0.6BNon-reasoning27.1#8350
12Gemma 3 27B (IT)26#1324
13SmolLM2-360M25.7#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-xeno-canto-call-duration · How It Works · Data refreshed daily, snapshot 2026-11-21.