Llama3-merge-biomed-8B [bfloat16] [rev: 5e7525f82b85]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1427 ± 34, rank #4829 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 67.78 | Accuracy (%) (5-shot) | 89.9 |
| Open LLM Leaderboard v1 - GSM8K | 59.59 | Accuracy (%) (5-shot) | 71.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.82 | Normalized accuracy (%) (25-shot) | 64.4 |
| Open LLM Leaderboard v1 - WinoGrande | 76.32 | Accuracy (%) (5-shot) | 47.6 |
| Open LLM Leaderboard v1 - HellaSwag | 81.43 | Normalized accuracy (%) (10-shot) | 45 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.42 | MC2 (%) (0-shot) | 44.7 |
Interactive version: theaggregate.ai/model?slug=llama3-merge-biomed-8b-bfloat16-rev-5e7525f82b85 · How It Works · Data refreshed daily, snapshot 2026-11-08.