open-llama-3B-v2-instruct: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1228 ± 37, rank #9434 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 39.69 | Accuracy (%) (5-shot) | 20.9 |
| Open LLM Leaderboard v1 - HellaSwag | 70.24 | Normalized accuracy (%) (10-shot) | 20.5 |
| Open LLM Leaderboard v1 - WinoGrande | 65.75 | Accuracy (%) (5-shot) | 19.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 38.48 | Normalized accuracy (%) (25-shot) | 15.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 37.96 | MC2 (%) (0-shot) | 7.1 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
Interactive version: theaggregate.ai/model?slug=open-llama-3b-v2-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.