Score vs. cost per question
Nous models in color, every other model in grey
Provider
1 model tested, compared with 77 models from other labs.
Nous#67Hermes 4 405B26.2% verification score41 tok/s0.3 s first token$0.01 / questionNous models in color, every other model in grey
Nous models in color, every other model in grey
Nous models highlighted against every model in this run · higher is better
Nous models highlighted against every model in this run · higher is better
Nous models highlighted against every model in this run · lower is better
Nous models highlighted against every model in this run · lower is better
Nous models highlighted against every model in this run · lower is better
Nous models highlighted against every model in this run · higher is better
| # | ||||||||
|---|---|---|---|---|---|---|---|---|
| 1 | Hermes 4 405B Nous · served by Nebius | 26.2 | 21 / 80 | 41 | 0.3 s | $0.01 | $1 / $3 | 131k |