dolphin-2.6-mistral-7B [float16] [rev: 61981ccfb93B]: benchmark results
Provider: Cognitive Computations. Access: Open.
Aggregate Rating 1409 ± 32, rank #5644 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.65 | MC2 (%) (0-shot) | 65.7 |
| Open LLM Leaderboard v1 - HellaSwag | 84.06 | Normalized accuracy (%) (10-shot) | 63.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.88 | Normalized accuracy (%) (25-shot) | 60.2 |
| Open LLM Leaderboard v1 - GSM8K | 46.1 | Accuracy (%) (5-shot) | 59.9 |
| Open LLM Leaderboard v1 - MMLU | 63.19 | Accuracy (%) (5-shot) | 58.9 |
| Open LLM Leaderboard v1 - WinoGrande | 77.58 | Accuracy (%) (5-shot) | 57 |
Interactive version: theaggregate.ai/model?slug=dolphin-2-6-mistral-7b-float16-rev-61981ccfb93b · How It Works · Data refreshed daily, snapshot 2026-11-08.