opt1.3B-10e4: benchmark results
Provider: Other.
Aggregate Rating 1137 ± 35, rank #10178 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 26.89 | Accuracy (%) (5-shot) | 14 |
| Open LLM Leaderboard v1 - WinoGrande | 58.41 | Accuracy (%) (5-shot) | 11.5 |
| Open LLM Leaderboard v1 - HellaSwag | 53.52 | Normalized accuracy (%) (10-shot) | 11.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 30.55 | Normalized accuracy (%) (25-shot) | 9.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 38.67 | MC2 (%) (0-shot) | 8.7 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
Interactive version: theaggregate.ai/model?slug=opt1-3b-10e4 · How It Works · Data refreshed daily, snapshot 2026-11-08.