Cohere xlarge v20220609 (52.4B): benchmark results
Provider: Other.
Aggregate Rating 1243 ± 33, rank #9304 of 10916 rated models, from 32 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Classic - HellaSwag | 81.1 | Exact Match (%) | 91.9 |
| RealToxicityPrompts | 0.01 | Toxic fraction | 85.4 |
| HELM Classic - IMDB | 95.57 | Exact Match (%) | 77.3 |
| HELM Classic - WikiFact | 33.55 | Exact Match (%) | 77.3 |
| HELM Classic - MATH | 13.54 | Equivalent (%) | 70.6 |
| HELM Classic - BLiMP | 83 | Exact Match (%) | 67.7 |
| HELM Classic - OpenbookQA | 55 | Exact Match (%) | 66.1 |
| HELM Classic - XSUM | 12.92 | ROUGE-2 (%) | 65.9 |
| HELM Classic - MS MARCO Regular | 27.33 | RR@10 (%) | 65.5 |
| HELM Classic - NaturalQuestions Closed Book | 31.25 | F1 (%) | 63.6 |
| HELM Classic - LegalSupport | 55.83 | Exact Match (%) | 63.2 |
| HELM Classic - Dyck | 59.4 | Exact Match (%) | 60.3 |
Interactive version: theaggregate.ai/model?slug=cohere-xlarge-v20220609-52-4b · How It Works · Data refreshed daily, snapshot 2026-11-08.