ELYZA-japanese-Llama-2-13B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1411 ± 20, rank #2050 of 2928 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 76.87 | Accuracy (%) (5-shot) | 51.3 |
| Open LLM Leaderboard v1 - GSM8K | 27.29 | Accuracy (%) (5-shot) | 45.2 |
| Open LLM Leaderboard v1 - HellaSwag | 80.89 | Normalized accuracy (%) (10-shot) | 42.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 57 | Normalized accuracy (%) (25-shot) | 36.5 |
| Open LLM Leaderboard v1 - MMLU | 54.38 | Accuracy (%) (5-shot) | 33.9 |
| pfgen-bench - Completion Mode - Fluency | 0.49 | Fluency Score | 33.9 |
| pfgen-bench - Completion Mode - Truthfulness | 0.63 | Truthfulness Score | 33.2 |
| pfgen-bench - Completion Mode - Helpfulness | 0.07 | Helpfulness Score | 32.9 |
| pfgen-bench - Completion Mode - Score | 0.4 | pfgen Score (mean of three) | 31.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.43 | MC2 (%) (0-shot) | 14.2 |
Interactive version: theaggregate.ai/model?slug=elyza-japanese-llama-2-13b · How It Works · Data refreshed daily, snapshot 2026-09-23.