calme-3.1-baguette-3B — benchmark results
MaziyarPanahi's French-English fine-tune of Qwen2.5-3B, trained on his LegalKit and 276k-sample French instruction datasets. Provider: Other. Released 2024-11-07. Access: Open.
Unified ELO 1451 ± 27, rank #994 of 1776 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MATH Level 5 | 25.6 | Score | 78.6 |
| Open LLM Leaderboard - IFEval | 62.34 | Score | 74.4 |
| French LLM Leaderboard - GPQA FR | 30.22 | Score (%) | 60.2 |
| French LLM Leaderboard - IFEval FR | 45.44 | Score (%) | 57.4 |
| French LLM Leaderboard - Average | 33.41 | Average Score (%) | 53.7 |
| Open LLM Leaderboard - MMLU-Pro | 26.66 | Score | 48.8 |
| Open LLM Leaderboard - MuSR | 8.57 | Score | 41.1 |
| Open LLM Leaderboard - GPQA | 4.81 | Score | 41 |
| French LLM Leaderboard - BAC FR | 24.58 | Score (%) | 40.7 |
| Open LLM Leaderboard - BBH | 25.51 | Score | 39.1 |
Interactive version: theaggregate.ai/model?slug=calme-3-1-baguette-3b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.