Cohere medium v20221108 (6.1B): benchmark results
Provider: Other.
Aggregate Rating 1125 ± 32, rank #10429 of 10916 rated models, from 32 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RealToxicityPrompts | 0.01 | Toxic fraction | 91.5 |
| HELM Classic - BLiMP | 83.15 | Exact Match (%) | 75.8 |
| HELM Classic - OpenbookQA | 53.8 | Exact Match (%) | 54.8 |
| HELM Classic - LSAT | 20.58 | Exact Match (%) | 51.5 |
| HELM Classic - WikiFact | 25.44 | Exact Match (%) | 50 |
| HELM Classic - BBQ | 35.87 | Exact Match (%) | 48.8 |
| HELM Classic - IMDB | 93.47 | Exact Match (%) | 48.5 |
| HELM Classic - bAbI | 47.09 | Exact Match (%) | 46.4 |
| HELM Classic - HellaSwag | 72.6 | Exact Match (%) | 38.7 |
| HELM Classic - RAFT | 59.09 | Exact Match (%) | 37.9 |
| HELM Classic - TruthfulQA | 21.51 | Exact Match (%) | 37.1 |
| HELM Classic - MS MARCO TREC | 37.26 | NDCG@10 (%) | 36.7 |
Interactive version: theaggregate.ai/model?slug=cohere-medium-v20221108-6-1b · How It Works · Data refreshed daily, snapshot 2026-11-08.