ALMA-13B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1328 ± 38, rank #8205 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 76.32 | Accuracy (%) (5-shot) | 47.6 |
| Open LLM Leaderboard v1 - HellaSwag | 80.29 | Normalized accuracy (%) (10-shot) | 40.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.83 | Normalized accuracy (%) (25-shot) | 36.2 |
| Open LLM Leaderboard v1 - MMLU | 49.92 | Accuracy (%) (5-shot) | 29.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 37.57 | MC2 (%) (0-shot) | 6.1 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
Interactive version: theaggregate.ai/model?slug=alma-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.