japanese-stablelm-instruct-gamma-7B: benchmark results

Provider: Other. Access: Open.

Unified ELO 1406 ± 20, rank #2088 of 2928 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
pfgen-bench - QA Mode - Helpfulness0.16Helpfulness Score46.1
pfgen-bench - QA Mode - Truthfulness0.73Truthfulness Score45.8
pfgen-bench - QA Mode - Score0.48pfgen Score (mean of three)44.8
pfgen-bench - QA Mode - Fluency0.55Fluency Score43.6
Open LLM Leaderboard v1 - GSM8K19.26Accuracy (%) (5-shot)40.5
Open LLM Leaderboard v1 - HellaSwag78.68Normalized accuracy (%) (10-shot)35.3
Open LLM Leaderboard v1 - MMLU54.82Accuracy (%) (5-shot)34.8
Open LLM Leaderboard v1 - WinoGrande73.72Accuracy (%) (5-shot)33.3
Open LLM Leaderboard v1 - ARC Challenge50.68Normalized accuracy (%) (25-shot)25
Open LLM Leaderboard v1 - TruthfulQA MC239.77MC2 (%) (0-shot)11.9

Interactive version: theaggregate.ai/model?slug=japanese-stablelm-instruct-gamma-7b · How It Works · Data refreshed daily, snapshot 2026-09-23.