all the models — AI benchmark observatory
← Models

Qwen3 32B

Alibaba Cloud / Qwen Team · open weight · qwen3-32b

Qwen3-32B is a large language model from Alibaba's Qwen3 series. It features 32.8 billion parameters, a 128k token context window, support for 119 languages, and hybrid thinking modes allowing switching between deep reasoning and fast responses. It demonstrates strong performance in reasoning, instruction-following, and agent capabilities.

Arena HardAIME 2024AIME 2025BFCLLiveCodeBenc

Benchmark scores

BenchmarkScore
Arena Hard0.94
AIME 20240.81
AIME 20250.73
BFCL0.70
LiveCodeBench0.66

Pricing

  • DeepInfra$0.08 / $0.28
  • Novita$0.10 / $0.44
  • Sambanova$0.40 / $0.80

Input / output per 1M tokens

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.