japanese-stablelm-base-gamma-7B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1402 ± 20, rank #2132 of 2928 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| pfgen-bench - Completion Mode - Fluency | 0.69 | Fluency Score | 71.6 |
| pfgen-bench - Completion Mode - Score | 0.58 | pfgen Score (mean of three) | 70 |
| pfgen-bench - Completion Mode - Helpfulness | 0.23 | Helpfulness Score | 68.4 |
| pfgen-bench - Completion Mode - Truthfulness | 0.82 | Truthfulness Score | 68.2 |
| Open LLM Leaderboard v1 - GSM8K | 17.82 | Accuracy (%) (5-shot) | 39.3 |
| Open LLM Leaderboard v1 - MMLU | 54.75 | Accuracy (%) (5-shot) | 34.7 |
| Open LLM Leaderboard v1 - WinoGrande | 73.95 | Accuracy (%) (5-shot) | 34.2 |
| Open LLM Leaderboard v1 - HellaSwag | 77.47 | Normalized accuracy (%) (10-shot) | 31 |
| Open LLM Leaderboard v1 - ARC Challenge | 50.34 | Normalized accuracy (%) (25-shot) | 24.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.2 | MC2 (%) (0-shot) | 16.3 |
Interactive version: theaggregate.ai/model?slug=japanese-stablelm-base-gamma-7b · How It Works · Data refreshed daily, snapshot 2026-09-23.