TPSTokens Per Second

Qwen3 72B

Alibaba / Qwen🇨🇳 China
active

Alibaba's top open-weights model. Hybrid thinking/non-thinking mode. Multilingual.

Compare with other models →
Context window128K tokens
Input / 1M tokens$0.4
Output / 1M tokens$1.2

Version History

Qwen3-72B-0806patch

Qwen3 72B patch release with bug fixes and improved instruction-following stability across multilingual prompts.

Qwen3-72Bmajor

Qwen3 72B ships with hybrid thinking/non-thinking modes. Claims top open-weights position on coding, math, and multilingual benchmarks.

Benchmark Scores

Full leaderboard →
82.5%
AIME 2025
72.3%
GPQA
91.2%
HumanEval
87.5%
MATH
87.1%
MMLU
79.5%
MMLU-Pro
65.0 tokens_per_sec
Speed (tok/s)