Jurassic-2 Grande (17B): benchmark results
Provider: Other.
Aggregate Rating 1310 ± 25, rank #8547 of 10916 rated models, from 61 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Classic - XSUM | 16.75 | ROUGE-2 (%) | 95.1 |
| HELM Classic - NarrativeQA | 73.68 | F1 (%) | 90.8 |
| HELM Classic - RAFT | 71.21 | Exact Match (%) | 87.9 |
| HELM Classic - BBQ | 49.4 | Exact Match (%) | 87.8 |
| HELM Classic - BoolQ | 82.6 | Exact Match (%) | 81.8 |
| HELM Classic - QuAC | 41.82 | F1 (%) | 81.5 |
| HELM Classic - Entity Data Imputation | 82.94 | Exact Match (%) | 80.3 |
| HELM Classic - MMLU | 47.53 | Exact Match (%) | 80.3 |
| HELM Classic - TruthfulQA | 34.76 | Exact Match (%) | 80.3 |
| HELM | 74.32 | Mean win rate (imported) | 80 |
| HELM Classic - NaturalQuestions Closed Book | 35.61 | F1 (%) | 77.3 |
| HELM Classic - LSAT | 22.03 | Exact Match (%) | 77.2 |
Interactive version: theaggregate.ai/model?slug=jurassic-2-grande-17b · How It Works · Data refreshed daily, snapshot 2026-11-08.