japanese-stablelm-instruct-beta-70B: benchmark results
Provider: Stability AI. Access: Open.
Aggregate Rating 1467 ± 46, rank #2915 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| pfgen-bench - QA Mode - Helpfulness | 0.2 | Helpfulness Score | 55.8 |
| pfgen-bench - QA Mode - Truthfulness | 0.78 | Truthfulness Score | 55.5 |
| pfgen-bench - QA Mode - Score | 0.51 | pfgen Score (mean of three) | 52.7 |
| Ebisu - JF-TE - Hit Rate@1 | 3.88 | Hit Rate@1 (%) | 47.4 |
| Ebisu - JF-TE - Hit Rate@5 | 10.9 | Hit Rate@5 (%) | 47.4 |
| pfgen-bench - QA Mode - Fluency | 0.55 | Fluency Score | 45.8 |
| Ebisu - JF-TE - Hit Rate@10 | 14.61 | Hit Rate@10 (%) | 42.1 |
| Ebisu - Overall | 10.17 | Mean Task Score (%) | 38.1 |
| Ebisu - JF-TE - F1 | 18.26 | Maximal-Term F1 (%) | 31.6 |
| Ebisu - JF-ICR | 3.19 | Accuracy (%) | 11.9 |
Interactive version: theaggregate.ai/model?slug=japanese-stablelm-instruct-beta-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.