J1-Grande v2 beta (17B): benchmark results
Provider: Other.
Aggregate Rating 1280 ± 36, rank #8978 of 10916 rated models, from 32 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Classic - XSUM | 15.18 | ROUGE-2 (%) | 85.4 |
| HELM Classic - IMDB | 95.73 | Exact Match (%) | 84.8 |
| HELM Classic - BBQ | 47.6 | Exact Match (%) | 80.5 |
| HELM Classic - NarrativeQA | 72.53 | F1 (%) | 80 |
| HELM Classic - OpenbookQA | 56 | Exact Match (%) | 77.4 |
| HELM Classic - BoolQ | 81.23 | Exact Match (%) | 77.3 |
| HELM Classic - MMLU | 44.51 | Exact Match (%) | 74.2 |
| HELM Classic - QuAC | 39.25 | F1 (%) | 73.8 |
| HELM Classic - TruthfulQA | 30.58 | Exact Match (%) | 72.7 |
| HELM Classic - RAFT | 67.88 | Exact Match (%) | 72 |
| HELM | 70.64 | Mean win rate (imported) | 70.8 |
| HELM Classic - Synthetic Reasoning Abstract | 28.61 | Exact Match (%) | 70.6 |
Interactive version: theaggregate.ai/model?slug=j1-grande-v2-beta-17b · How It Works · Data refreshed daily, snapshot 2026-11-08.