J1-Grande v1 (17B): benchmark results
Provider: Other.
Aggregate Rating 1184 ± 33, rank #9698 of 10916 rated models, from 32 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Classic - Dyck | 69.6 | Exact Match (%) | 83.1 |
| HELM Classic - IMDB | 95.3 | Exact Match (%) | 74.2 |
| HELM Classic - Synthetic Reasoning Abstract | 24.72 | Exact Match (%) | 66.2 |
| HELM Classic - RAFT | 65.76 | Exact Match (%) | 65.2 |
| HELM Classic - QuAC | 36.24 | F1 (%) | 61.5 |
| HELM Classic - Entity Matching | 83.08 | Exact Match (%) | 60.6 |
| HELM Classic - NarrativeQA | 67.18 | F1 (%) | 60 |
| HELM Classic - BBQ | 36.1 | Exact Match (%) | 56.1 |
| HELM Classic - CNN/DailyMail | 14.31 | ROUGE-2 (%) | 53.7 |
| HELM Classic - XSUM | 12.22 | ROUGE-2 (%) | 53.7 |
| HELM Classic - WikiFact | 26.87 | Exact Match (%) | 53 |
| HELM Classic - GSM8K | 5.37 | Exact Match (%) | 48.5 |
Interactive version: theaggregate.ai/model?slug=j1-grande-v1-17b · How It Works · Data refreshed daily, snapshot 2026-11-08.