FLAMA-0.5-3B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1161 ± 38, rank #9827 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 67.65 | Normalized accuracy (%) (10-shot) | 18.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.11 | MC2 (%) (0-shot) | 16.1 |
| Open LLM Leaderboard v1 - WinoGrande | 62.12 | Accuracy (%) (5-shot) | 15.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 37.97 | Normalized accuracy (%) (25-shot) | 14.9 |
| Open LLM Leaderboard v1 - GSM8K | 0.83 | Accuracy (%) (5-shot) | 14.3 |
| Open LLM Leaderboard v1 - MMLU | 25.73 | Accuracy (%) (5-shot) | 9.6 |
Interactive version: theaggregate.ai/model?slug=flama-0-5-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.