mistralv1_gsm8k_merged: benchmark results
Provider: Mistral. Access: Open.
Aggregate Rating 1404 ± 33, rank #5903 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 78.61 | Accuracy (%) (5-shot) | 64.3 |
| Open LLM Leaderboard v1 - GSM8K | 47.99 | Accuracy (%) (5-shot) | 61.2 |
| Open LLM Leaderboard v1 - MMLU | 63.04 | Accuracy (%) (5-shot) | 58 |
| Open LLM Leaderboard v1 - HellaSwag | 83.11 | Normalized accuracy (%) (10-shot) | 56 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.35 | Normalized accuracy (%) (25-shot) | 52.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 39.55 | MC2 (%) (0-shot) | 11.3 |
Interactive version: theaggregate.ai/model?slug=mistralv1-gsm8k-merged · How It Works · Data refreshed daily, snapshot 2026-11-08.