mt0-xl: benchmark results
Provider: BigScience. Access: Open.
Aggregate Rating 1307 ± 44, rank #8596 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Greek MMLU - Other | 52.51 | Accuracy (%) | 44.4 |
| Greek MMLU - Social Sciences | 54.21 | Accuracy (%) | 42 |
| Greek MMLU - Greek-Specific | 52.24 | Accuracy (%) | 39.5 |
| Greek MMLU | 49.96 | Accuracy (%) | 35.8 |
| Greek MMLU - Humanities | 47.88 | Accuracy (%) | 33.3 |
| Greek MMLU - STEM | 46.44 | Accuracy (%) | 30.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
| Open Korean LLM - Ko-IFEval | 19.19 | Strict accuracy, prompt/instruction mean (%) | 15.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 1.52 | Exact match, flexible extract (%) | 13.9 |
| Open Korean LLM - Ko-Winogrande | 51.3 | Accuracy (%) | 6.1 |
| Open Korean LLM - KorNAT-Helpful | 39.1 | Normalized accuracy (%) | 4.5 |
Interactive version: theaggregate.ai/model?slug=mt0-xl · How It Works · Data refreshed daily, snapshot 2026-11-08.