30B-Epsilon: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1381 ± 35, rank #6812 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 59.03 | MC2 (%) (0-shot) | 73.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.05 | Normalized accuracy (%) (25-shot) | 61 |
| Open LLM Leaderboard v1 - HellaSwag | 83.59 | Normalized accuracy (%) (10-shot) | 59.9 |
| Open LLM Leaderboard v1 - WinoGrande | 77.66 | Accuracy (%) (5-shot) | 57.6 |
| Open LLM Leaderboard v1 - GSM8K | 24.56 | Accuracy (%) (5-shot) | 43.6 |
| Open LLM Leaderboard v1 - MMLU | 56.89 | Accuracy (%) (5-shot) | 40.2 |
Interactive version: theaggregate.ai/model?slug=30b-epsilon · How It Works · Data refreshed daily, snapshot 2026-11-08.