Chocolatine-3B-Instruct-DPO-Revised: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1421 ± 38, rank #5118 of 10916 rated models, from 56 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 44.53 | Score | 81.1 |
| Open LLM Leaderboard - GPQA | 32.21 | Score | 76.5 |
| Open LLM Leaderboard - BBH | 55.4 | Score | 75.2 |
| Open LLM Leaderboard - MMLU-Pro | 39.89 | Score | 73.4 |
| Open LLM Leaderboard - IFEval | 56.23 | Score | 68.2 |
| Open LLM Leaderboard - MATH Level 5 | 18.05 | Score | 67.5 |
| Open Japanese LLM - Xlsum JA Rouge1 | 27.72 | Score (%) | 66.1 |
| Open Japanese LLM - Xlsum JA RougeLsum | 23.16 | Score (%) | 63.5 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 69.18 | Score (%) | 53.1 |
| Open Japanese LLM - Wiki NER SET F1 | 5.31 | Score (%) | 51.2 |
| Open Japanese LLM - CG | 5.42 | Score (%) | 45.9 |
| Open Japanese LLM - Mbpp Pylint Check | 16.27 | Score (%) | 43.8 |
Interactive version: theaggregate.ai/model?slug=chocolatine-3b-instruct-dpo-revised · How It Works · Data refreshed daily, snapshot 2026-11-08.