Models

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

ModelProviderSourcesResults
Muse Spark 1.1Meta214
Nemotron 3 SuperNVIDIA213
Nova Lite 1.0Amazon28
Qwen2.5 72B InstructAlibaba29
Qwen3 235B A22BAlibaba214
Qwen3 235B A22B Thinking 2507Alibaba29
Qwen3 30B A3BAlibaba212
Qwen3 Coder 480B A35BAlibaba213
Qwen3 MaxAlibaba29
Qwen3 Next 80B A3B InstructAlibaba210
Qwen3 VL 235B A22B InstructAlibaba210
Qwen3 VL 235B A22B ThinkingAlibaba29
R1 0528DeepSeek29
Step 3.5 FlashStepfun210
Trinity Large ThinkingArcee Ai213
ai21-jamba-large-1.7AI21 Labs25
ai21-jamba-mini-1.7AI21 Labs25
c4ai-aya-expanse-32bCohere28
c4ai-aya-expanse-8bCohere28
chatgpt-4o-latest-20250326OpenAI210
claude-3-7-sonnet-20250219Anthropic218
claude-3-haiku-20240307Anthropic29
claude-3-opus-20240229Anthropic29
gemini-2.5-flash-preview-09-2025Google213
gemma-2-2b-itGoogle29
gemma-2-9b-itGoogle29
gpt-5.3-chat-latestOpenAI210
gpt-oss-20bOpenAI215
granite-3.1-8b-instructIBM214
granite-4.0-h-smallIBM25
grok-3xAI25
grok-4-1-fastxAI23
grok-4-fastxAI23
grok-4-fast-non-reasoningxAI25
grok-4.20-beta-0309-reasoningxAI211
grok-4.20-multi-agent-beta-0309xAI211
llama-2-70b-chatMeta29
llama-3.1-nemotron-ultra-253b-v1NVIDIA213
llama-4-maverick-17b-128e-instruct-fp8Meta210
mimo-v2-flashXiaomi220
mixtral-8x7b-instruct-v0.1Mistral29
nanbeige4-3b-thinking-2511Nanbeige211
o1OpenAI212
olmo-3-32b-thinkAi2210
qwen3-0.6bAlibaba219
qwen3-1.7bAlibaba214
qwen3-4bAlibaba28
qwen3-4b-instruct-2507Alibaba219
qwq-32bAlibaba29
snowflake-arctic-instructSnowflake28

Want two models side by side? Compare models.