J1-Jumbo v1 (178B): benchmark results
Provider: Other.
Aggregate Rating 1204 ± 36, rank #9596 of 10916 rated models, from 32 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Classic - LSAT | 23.19 | Exact Match (%) | 88.2 |
| HELM Classic - bAbI | 54.34 | Exact Match (%) | 78.3 |
| HELM Classic - RAFT | 68.11 | Exact Match (%) | 75.8 |
| HELM Classic - NarrativeQA | 69.5 | F1 (%) | 69.2 |
| HELM Classic - Synthetic Reasoning Abstract | 26.26 | Exact Match (%) | 69.1 |
| HELM Classic - BBQ | 37.77 | Exact Match (%) | 68.3 |
| HELM Classic - XSUM | 12.93 | ROUGE-2 (%) | 68.3 |
| HELM Classic - BoolQ | 77.57 | Exact Match (%) | 65.2 |
| HELM Classic - Entity Matching | 84.15 | Exact Match (%) | 65.2 |
| HELM Classic - HellaSwag | 76.5 | Exact Match (%) | 64.5 |
| HELM Classic - IMDB | 94.33 | Exact Match (%) | 63.6 |
| HELM Classic - CivilComments | 55.3 | Exact Match (%) | 60.6 |
Interactive version: theaggregate.ai/model?slug=j1-jumbo-v1-178b · How It Works · Data refreshed daily, snapshot 2026-11-08.