all the models — AI benchmark observatory
← Models

Qwen2.5 72B Instruct

Alibaba Cloud / Qwen Team · open weight · qwen-2.5-72b-instruct

Qwen2.5-72B-Instruct is an instruction-tuned 72 billion parameter language model, part of the Qwen2.5 series. It is designed to follow instructions, generate long texts (over 8K tokens), understand structured data (e.g., tables), and generate structured outputs, especially JSON. The model supports multilingual capabilities across over 29 languages.

GSM8kMT-BenchHumanEvalIFEvalMATHArena Hard

Benchmark scores

BenchmarkScore
GSM8k0.96
MT-Bench0.94
HumanEval0.87
IFEval0.84
MATH0.83
Arena Hard0.81
MMLU-Pro0.71
LiveCodeBench0.56
GPQA0.49

Pricing

  • DeepInfra$0.36 / $0.40

Input / output per 1M tokens

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.