Dolphin-2.8-slerp [float16] [rev: 1da8b3280f67]: benchmark results
Provider: Cognitive Computations. Access: Open.
Aggregate Rating 1443 ± 36, rank #4063 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 67.63 | Accuracy (%) (5-shot) | 84 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 65.22 | MC2 (%) (0-shot) | 83.4 |
| Open LLM Leaderboard v1 - WinoGrande | 82 | Accuracy (%) (5-shot) | 81.7 |
| Open LLM Leaderboard v1 - HellaSwag | 86.43 | Normalized accuracy (%) (10-shot) | 81 |
| Open LLM Leaderboard v1 - ARC Challenge | 68 | Normalized accuracy (%) (25-shot) | 78.9 |
| Open LLM Leaderboard v1 - MMLU | 64.39 | Accuracy (%) (5-shot) | 69.5 |
Interactive version: theaggregate.ai/model?slug=dolphin-2-8-slerp-float16-rev-1da8b3280f67 · How It Works · Data refreshed daily, snapshot 2026-11-08.