Llama-2-ko-7B-Chat [bfloat16] [rev: 3293b98cd820]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1191 ± 36, rank #9669 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 66.61 | Accuracy (%) (5-shot) | 20.5 |
| Open LLM Leaderboard v1 - HellaSwag | 67.12 | Normalized accuracy (%) (10-shot) | 18.2 |
| Open LLM Leaderboard v1 - GSM8K | 1.67 | Accuracy (%) (5-shot) | 17.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 40.44 | Normalized accuracy (%) (25-shot) | 16.7 |
| Open LLM Leaderboard v1 - MMLU | 30.19 | Accuracy (%) (5-shot) | 16.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 35.45 | MC2 (%) (0-shot) | 2.2 |
Interactive version: theaggregate.ai/model?slug=llama-2-ko-7b-chat-bfloat16-rev-3293b98cd820 · How It Works · Data refreshed daily, snapshot 2026-11-08.