dolphin-2.6-mistral-7B [bfloat16] [rev: 61981ccfb93B]: benchmark results
Provider: Cognitive Computations. Access: Open.
Aggregate Rating 1410 ± 32, rank #5625 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.67 | MC2 (%) (0-shot) | 65.8 |
| Open LLM Leaderboard v1 - HellaSwag | 84.05 | Normalized accuracy (%) (10-shot) | 63.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.05 | Normalized accuracy (%) (25-shot) | 61 |
| Open LLM Leaderboard v1 - GSM8K | 45.87 | Accuracy (%) (5-shot) | 59.7 |
| Open LLM Leaderboard v1 - MMLU | 63.2 | Accuracy (%) (5-shot) | 58.9 |
| Open LLM Leaderboard v1 - WinoGrande | 77.66 | Accuracy (%) (5-shot) | 57.6 |
Interactive version: theaggregate.ai/model?slug=dolphin-2-6-mistral-7b-bfloat16-rev-61981ccfb93b · How It Works · Data refreshed daily, snapshot 2026-11-08.