BAGEL - bioRxiv: leaderboard
BAGEL questions asking for the interpretation of results in animal-focused bioRxiv preprints from behavior, ecology, evolution and zoology. 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 2,183 bioRxiv questions (result interpretation of animal-focused preprints) 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: Estimated already saturated. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.4 | 94.41 | #138 | |
| 2 | Phi-4 | 92.44 | #1951 | |
| 3 | Qwen 3 32B | Non-reasoning | 91.85 | #983 |
| 4 | Qwen 3 14B | Non-reasoning | 91.11 | #1284 |
| 5 | Claude Opus 4.6 | 91.07 | #114 | |
| 6 | Gemma 3 27B (IT) | 90.98 | #1341 | |
| 7 | Qwen 3 8B | Non-reasoning | 89.92 | #1890 |
| 8 | Qwen 3 4B | Non-reasoning | 89.01 | #2379 |
| 9 | Llama 3.1 8B Instruct | 88.82 | #4655 | |
| 10 | Mistral 7B Instruct (v0.3) | 85.57 | #6759 | |
| 11 | gemma-7B | 85.43 | #7115 | |
| 12 | SmolLM2-360M | 25.1 | #9572 | |
| 13 | Qwen 3 0.6B | Non-reasoning | 24.05 | #8357 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=bagel-biorxiv · How It Works · Data refreshed daily, snapshot 2026-11-22.