ModelProviderParamsContextMMLUReasoningCoding
GPT-4oOpenAI~200B128K88.7HighHigh
Claude 3.5 SonnetAnthropicUnknown200K88.7HighHigh
Gemini 1.5 ProGoogleUnknown2M85.9HighHigh
Llama 3.1 405BMeta405B128K88.6HighMedium
Mistral LargeMistralUnknown128K84.0MediumMedium