Jurassic-2 Large (7.5B): benchmark results
Provider: Other.
Aggregate Rating 1185 ± 40, rank #9692 of 10916 rated models, from 30 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Classic - IMDB | 95.63 | Exact Match (%) | 82.6 |
| HELM Classic - XSUM | 14.21 | ROUGE-2 (%) | 78 |
| HELM Classic - LSAT | 21.74 | Exact Match (%) | 73.5 |
| HELM Classic - CivilComments | 57.04 | Exact Match (%) | 69.7 |
| HELM Classic - MS MARCO TREC | 46.44 | NDCG@10 (%) | 66.7 |
| HELM Classic - bAbI | 50.4 | Exact Match (%) | 63.8 |
| HELM Classic - LegalSupport | 55.83 | Exact Match (%) | 63.2 |
| HELM Classic - Entity Matching | 83.57 | Exact Match (%) | 62.1 |
| HELM Classic - TruthfulQA | 24.46 | Exact Match (%) | 59.1 |
| HELM Classic - MS MARCO Regular | 24.69 | RR@10 (%) | 58.6 |
| HELM Classic - Dyck | 55.93 | Exact Match (%) | 54.4 |
| HELM Classic - Synthetic Reasoning Natural | 17.62 | F1 (%) | 54.4 |
Interactive version: theaggregate.ai/model?slug=jurassic-2-large-7-5b · How It Works · Data refreshed daily, snapshot 2026-11-08.