calme-3.2-instruct-3B: benchmark results
Provider: MaziyarPanahi. Access: Open.
Aggregate Rating 1452 ± 30, rank #3666 of 10916 rated models, from 60 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MATH Level 5 | 21.68 | Score | 74 |
| Open LLM Leaderboard - IFEval | 55.33 | Score | 66.9 |
| Open Japanese LLM - Mbpp Pylint Check | 71.49 | Score (%) | 64.7 |
| Open Japanese LLM - CG | 37.35 | Score (%) | 64.4 |
| Open Japanese LLM - Wiki NER SET F1 | 7.08 | Score (%) | 62.7 |
| French LLM Leaderboard - GPQA FR | 30.04 | Score (%) | 57.4 |
| Open LLM Leaderboard - MMLU-Pro | 36.53 | Score | 57.2 |
| Open Japanese LLM - Wiki Coreference SET F1 | 3.31 | Score (%) | 55 |
| French LLM Leaderboard - BAC FR | 27.82 | Score (%) | 46.3 |
| Open LLM Leaderboard - MuSR | 40.47 | Score | 46.1 |
| French LLM Leaderboard - Average | 24.08 | Mean Normalized Score (%) | 44.4 |
| Open Japanese LLM - Jsick Exact Match | 76.42 | Score (%) | 43.8 |
Interactive version: theaggregate.ai/model?slug=calme-3-2-instruct-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.