ELYZA-japanese-Llama-2-7B-instruct: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1300 ± 15, rank #8746 of 10916 rated models, from 72 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Econometrics | 33.33 | Accuracy (%) | 80.1 |
| MMLU-by-task - Human Sexuality | 61.07 | Accuracy (%) | 68.2 |
| MMLU-by-task - Astronomy | 51.97 | Accuracy (%) | 66.8 |
| MMLU-by-task - Conceptual Physics | 42.55 | Accuracy (%) | 65.8 |
| MMLU-by-task - High School Mathematics | 28.52 | Accuracy (%) | 64.7 |
| MMLU-by-task - Logical Fallacies | 57.67 | Accuracy (%) | 60.8 |
| MMLU-by-task - Miscellaneous | 68.58 | Accuracy (%) | 59.7 |
| MMLU-by-task - College Medicine | 43.93 | Accuracy (%) | 59.4 |
| MMLU-by-task - Human Aging | 57.85 | Accuracy (%) | 58.9 |
| MMLU-by-task - High School Government And Politics | 69.95 | Accuracy (%) | 58.6 |
| MMLU-by-task - Prehistory | 54.63 | Accuracy (%) | 58.2 |
| MMLU-by-task - Clinical Knowledge | 51.7 | Accuracy (%) | 58 |
Interactive version: theaggregate.ai/model?slug=elyza-japanese-llama-2-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.