dolphin-2.1-mistral-7B [float16] [rev: aa5bd48c8b30]: benchmark results
Provider: Cognitive Computations.
Aggregate Rating 1407 ± 34, rank #5761 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 85 | Normalized accuracy (%) (10-shot) | 70.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.57 | MC2 (%) (0-shot) | 65.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.99 | Normalized accuracy (%) (25-shot) | 65.1 |
| Open LLM Leaderboard v1 - MMLU | 63.44 | Accuracy (%) (5-shot) | 60.7 |
| Open LLM Leaderboard v1 - WinoGrande | 77.9 | Accuracy (%) (5-shot) | 59.3 |
| Open LLM Leaderboard v1 - GSM8K | 20.09 | Accuracy (%) (5-shot) | 41 |
Interactive version: theaggregate.ai/model?slug=dolphin-2-1-mistral-7b-float16-rev-aa5bd48c8b30 · How It Works · Data refreshed daily, snapshot 2026-11-08.