ALL EVALUATED HOSTS· [46] MODELS
EVALUATED HOSTS · [46] MODELS
Anthropic
10.1
/20
13.2
/20
10.5
/20
11.1
/20
9.2
/20
14
/20
13.2
/20
10.8
/20
13.9
/20
Google
8.4
/20
11.9
/20
10.6
/20
14.4
/20
OPEN WEIGHTS
16.1
/20
11.1
/20
OPEN WEIGHTS
14.7
/20
14.4
/20
12.7
/20
OpenAI
10.6
/20
10.5
/20
11.1
/20
8.8
/20
15.2
/20
14.9
/20
13.4
/20
12.7
/20
Cohere
6.5
/20
COMMERCIAL USE RESTRICTED
xAI
10.2
/20
10.8
/20
13.9
/20
Meta
9
/20
OPEN WEIGHTS
10.4
/20
OPEN WEIGHTS
12.1
/20
OPEN WEIGHTS
14.4
/20
Mistral
9.5
/20
COMMERCIAL USE RESTRICTED
13.6
/20
OPEN WEIGHTS
12.1
/20
OPEN WEIGHTS
DeepSeek
9.4
/20
OPEN WEIGHTS
14.2
/20
OPEN WEIGHTS
MiniMax
14.2
/20
Zhipu AI
13.9
/20
OPEN WEIGHTS
14.1
/20
OPEN WEIGHTS
Alibaba
14.1
/20
OPEN WEIGHTS
13.9
/20
OPEN WEIGHTS
Other
14
/20
OPEN WEIGHTS
12.5
/20
OPEN WEIGHTS