Models

539 models with published results from our own benchmarks and licensed sources. Open a model to see every result, with its source and date.

ModelProviderSourcesResults
Claude Sonnet 4Anthropic320
Claude Sonnet 5.5Anthropic322
Command R+ (08-2024)Cohere311
DeepSeek V3DeepSeek311
DeepSeek V3.1DeepSeek320
GLM 4.7 FlashZ.ai315
GLM 5.1Z.ai319
GLM 5.2Z.ai319
GPT-5OpenAI318
GPT-5 MiniOpenAI325
GPT-5 NanoOpenAI324
GPT-5.1OpenAI329
Gemini 2.5 FlashGoogle325
Gemini 3.5 FlashGoogle334
Gemma 4 26B A4BGoogle315
Gemma 4 31BGoogle316
Grok 4.5xAI318
Kimi K2 0711Moonshot AI317
Kimi K2 0905Moonshot AI312
Llama 3.1 8B InstructMeta317
Llama 3.2 1B InstructMeta317
Llama 3.2 3B InstructMeta317
Llama 3.3 70B InstructMeta317
MiniMax M2.1MiniMax311
Mistral Large 3 2512Mistral315
Mistral Medium 3Mistral325
Mistral Medium 3.1Mistral312
Mistral Small 3Mistral311
Mistral Small 3.2 24BMistral325
Nova Micro 1.0Amazon316
Nova Pro 1.0Amazon316
Qwen3 14BAlibaba324
Qwen3 235B A22B Instruct 2507Alibaba326
Qwen3 30B A3B Instruct 2507Alibaba325
Qwen3 8BAlibaba324
Qwen3 Next 80B A3B ThinkingAlibaba311
Qwen3.5 397B A17BAlibaba318
Qwen3.5-122B-A10BAlibaba315
Qwen3.5-27BAlibaba315
Qwen3.5-35B-A3BAlibaba315
Qwen3.5-FlashAlibaba315
Qwen3.6 PlusAlibaba319
R1DeepSeek311
claude-opus-4Anthropic321
gemini-3-flashGoogle330
gemini-3-proGoogle323
gemini-3-pro-previewGoogle324
gpt-oss-120bOpenAI312
grok-4-0709xAI326
grok-4-1-fast-non-reasoningxAI313

Want two models side by side? Compare models.