phi-2-OpenHermes-2.5-v2: benchmark results
Provider: g-ronimo. Access: Open.
Aggregate Rating 1361 ± 33, rank #7406 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 40.41 | Accuracy (%) (5-shot) | 55.7 |
| Open LLM Leaderboard v1 - WinoGrande | 75.22 | Accuracy (%) (5-shot) | 40.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.45 | Normalized accuracy (%) (25-shot) | 39.8 |
| Open LLM Leaderboard v1 - MMLU | 56.43 | Accuracy (%) (5-shot) | 39.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.89 | MC2 (%) (0-shot) | 28.9 |
| Open LLM Leaderboard v1 - HellaSwag | 74.57 | Normalized accuracy (%) (10-shot) | 24.8 |
Interactive version: theaggregate.ai/model?slug=phi-2-openhermes-2-5-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.