LFM2.5-350M: benchmark results
Provider: Liquid AI. Access: Open.
Aggregate Rating 1226 ± 48, rank #9441 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Kurakurai French LLM - BFCL v2 | 58.18 | Accuracy (%) | 58.6 |
| Kurakurai French LLM - IFEval | 51.66 | Accuracy (%) | 43.9 |
| Kurakurai French LLM - MultiIF | 33.44 | Accuracy (%) | 41.5 |
| Kurakurai French LLM - MMLU-Pro | 16.8 | Accuracy (%) | 37.8 |
| Kurakurai French LLM - Global MMLU | 39.8 | Accuracy (%) | 34.1 |
| Kurakurai French LLM - MGSM | 21.28 | Accuracy (%) | 26.8 |
| Kurakurai French LLM - GPQA Diamond | 22.8 | Accuracy (%) | 24.4 |
| Kurakurai French LLM - MBPP | 19.44 | pass@1 (%) | 24.4 |
| Kurakurai French LLM - MATH-500 | 11.4 | Accuracy (%) | 22 |
| Kurakurai French LLM - HumanEval+ | 10.37 | pass@1 (%) | 19.5 |
| Kurakurai French LLM - AIME 2025 | 0 | Accuracy (%) | 15.9 |
| Kurakurai French LLM - AIME 2024 | 0 | Accuracy (%) | 13.4 |
Interactive version: theaggregate.ai/model?slug=lfm2-5-350m · How It Works · Data refreshed daily, snapshot 2026-11-08.