ELYZA-japanese-Llama-2-13B-fast: benchmark results

Provider: Other. Access: Open.

Unified ELO 1409 ± 20, rank #2060 of 2928 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande77.19Accuracy (%) (5-shot)54
Open LLM Leaderboard v1 - GSM8K25.47Accuracy (%) (5-shot)44
Open LLM Leaderboard v1 - HellaSwag80.73Normalized accuracy (%) (10-shot)42.2
Open LLM Leaderboard v1 - ARC Challenge55.89Normalized accuracy (%) (25-shot)34.4
Open LLM Leaderboard v1 - MMLU54.4Accuracy (%) (5-shot)33.9
pfgen-bench - Completion Mode - Helpfulness0.06Helpfulness Score29.9
pfgen-bench - Completion Mode - Score0.37pfgen Score (mean of three)26.5
pfgen-bench - Completion Mode - Fluency0.46Fluency Score26.2
pfgen-bench - Completion Mode - Truthfulness0.6Truthfulness Score25.9
Open LLM Leaderboard v1 - TruthfulQA MC240.31MC2 (%) (0-shot)13.6

Interactive version: theaggregate.ai/model?slug=elyza-japanese-llama-2-13b-fast · How It Works · Data refreshed daily, snapshot 2026-09-23.