ELYZA-japanese-Llama-2-7B-fast: benchmark results

Provider: Other. Access: Open.

Unified ELO 1344 ± 20, rank #2509 of 2928 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
pfgen-bench - Completion Mode - Helpfulness0.05Helpfulness Score27.8
Open LLM Leaderboard v1 - WinoGrande71.59Accuracy (%) (5-shot)26.9
Open LLM Leaderboard v1 - ARC Challenge51.88Normalized accuracy (%) (25-shot)26.5
Open LLM Leaderboard v1 - HellaSwag75.46Normalized accuracy (%) (10-shot)26.5
Open LLM Leaderboard v1 - GSM8K6.29Accuracy (%) (5-shot)25.4
pfgen-bench - Completion Mode - Fluency0.45Fluency Score25.2
pfgen-bench - Completion Mode - Score0.36pfgen Score (mean of three)24.8
pfgen-bench - Completion Mode - Truthfulness0.59Truthfulness Score24.3
Open LLM Leaderboard v1 - MMLU44.34Accuracy (%) (5-shot)23.3
Open LLM Leaderboard v1 - TruthfulQA MC236.45MC2 (%) (0-shot)3.8

Interactive version: theaggregate.ai/model?slug=elyza-japanese-llama-2-7b-fast · How It Works · Data refreshed daily, snapshot 2026-09-23.