bigstral-12B-32k: benchmark results
Provider: Other. Released 2024-03-06. Access: Open.
Unified ELO 1405 ± 1, rank #1115 of 1392 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 15.86 | Score | 84.1 |
| Open Chinese LLM - TruthfulQA MC | 58.81 | Accuracy (%) | 78.9 |
| Open LLM Leaderboard - GPQA | 5.7 | Score | 47.8 |
| Open Korean LLM Leaderboard | 35 | Average Score (%) | 46.9 |
| Open LLM Leaderboard - IFEval | 41.94 | Score | 42.8 |
| Open LLM Leaderboard - BBH | 25.56 | Score | 39.3 |
| Open LLM Leaderboard - MMLU-Pro | 18.24 | Score | 27.8 |
| Open Chinese LLM - WinoGrande | 61.4 | Accuracy (%) | 26.9 |
| Open Chinese LLM - ARC Challenge | 46.5 | Accuracy (%) | 23.1 |
| Open Chinese LLM - HellaSwag | 54.09 | Accuracy (%) | 19 |
| Open Chinese LLM - CMMLU | 45.93 | Accuracy (%) | 15.1 |
| Open Chinese LLM Leaderboard | 48.07 | Average Score (%) | 13.5 |
Interactive version: theaggregate.ai/model?slug=bigstral-12b-32k · How It Works · Data refreshed daily, snapshot 2026-09-05.