ALMA-7B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1257 ± 41, rank #9195 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 72.38 | Accuracy (%) (5-shot) | 28.9 |
| Open LLM Leaderboard v1 - HellaSwag | 75.5 | Normalized accuracy (%) (10-shot) | 26.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 50.34 | Normalized accuracy (%) (25-shot) | 24.7 |
| Open LLM Leaderboard v1 - MMLU | 38.04 | Accuracy (%) (5-shot) | 19.8 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 35.64 | MC2 (%) (0-shot) | 2.5 |
Interactive version: theaggregate.ai/model?slug=alma-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.