Luth-0.6B-Instruct: benchmark results
Provider: Other. Released 2025-08-06. Access: Open.
Unified ELO 1353 ± 29, rank #2212 of 2656 rated models, from 49 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Kurakurai French LLM - BFCL v2 | 61.72 | Accuracy (%) | 69 |
| Kurakurai French LLM - AIME 2025 | 1.33 | Accuracy (%) | 61 |
| Kurakurai French LLM - MATH-500 | 44.74 | Accuracy (%) | 61 |
| Kurakurai French LLM - AIME 2024 | 2 | Accuracy (%) | 59.8 |
| Kurakurai French LLM - MGSM | 58.52 | Accuracy (%) | 58.5 |
| Kurakurai French LLM - HumanEval+ | 30.25 | pass@1 (%) | 53.7 |
| Kurakurai French LLM - MMLU-Pro | 25.4 | Accuracy (%) | 53.7 |
| Open Portuguese LLM - FaQuAD NLI | 67.31 | Macro F1 (%) | 53.6 |
| Kurakurai French LLM - MBPP | 34.74 | pass@1 (%) | 46.3 |
| Kurakurai French LLM - MultiIF | 33.77 | Accuracy (%) | 46.3 |
| Kurakurai French LLM - GPQA Diamond | 25.6 | Accuracy (%) | 43.9 |
| Kurakurai French LLM - IFEval | 51.23 | Accuracy (%) | 41.5 |
Interactive version: theaggregate.ai/model?slug=luth-0-6b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.