Mistral-7B-instruct-v0.2-summ-sft-bf16-e1 [Adapter]: benchmark results
Provider: Mistral. Access: Open.
Aggregate Rating 1394 ± 33, rank #6352 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 64.72 | MC2 (%) (0-shot) | 82.6 |
| Open LLM Leaderboard v1 - HellaSwag | 83.32 | Normalized accuracy (%) (10-shot) | 57.9 |
| Open LLM Leaderboard v1 - GSM8K | 39.2 | Accuracy (%) (5-shot) | 54.1 |
| Open LLM Leaderboard v1 - WinoGrande | 76.72 | Accuracy (%) (5-shot) | 50.1 |
| Open LLM Leaderboard v1 - MMLU | 60.79 | Accuracy (%) (5-shot) | 49.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.58 | Normalized accuracy (%) (25-shot) | 48.4 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-instruct-v0-2-summ-sft-bf16-e1-adapter · How It Works · Data refreshed daily, snapshot 2026-11-08.