Jurassic-2 Jumbo (178B): benchmark results
Provider: Other.
Aggregate Rating 1344 ± 24, rank #7869 of 10916 rated models, from 61 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Classic - LegalSupport | 63.87 | Exact Match (%) | 100 |
| HELM Classic - XSUM | 18.16 | ROUGE-2 (%) | 100 |
| HELM Classic - Entity Data Imputation | 84.1 | Exact Match (%) | 93.9 |
| HELM Classic - RAFT | 74.62 | Exact Match (%) | 93.9 |
| HELM Classic - TruthfulQA | 43.73 | Exact Match (%) | 90.9 |
| HELM | 82.44 | Mean win rate (imported) | 90.8 |
| HELM Classic - QuAC | 43.49 | F1 (%) | 90.8 |
| HELM Classic - BBQ | 55.03 | Exact Match (%) | 90.2 |
| HELM Classic - MS MARCO TREC | 66.06 | NDCG@10 (%) | 90 |
| HELM Classic - MS MARCO Regular | 39.84 | RR@10 (%) | 89.7 |
| HELM Classic - NaturalQuestions Closed Book | 38.53 | F1 (%) | 89.4 |
| HELM Classic - NarrativeQA | 73.32 | F1 (%) | 89.2 |
Interactive version: theaggregate.ai/model?slug=jurassic-2-jumbo-178b · How It Works · Data refreshed daily, snapshot 2026-11-08.