QvQ-72B-Preview: Benchmarks, Pricing & Context Window
QvQ-72B-Preview is a language model from Qwen, released in December 2024, with multimodal input.
An experimental research model focusing on advanced visual reasoning and step-by-step cognitive capabilities. Achieves strong performance on multi-modal science and mathematics tasks, though exhibits some limitations such as potential
QvQ-72B-Preview benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for QvQ-72B-Preview across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How QvQ-72B-Preview holds up as conversations get longer.
Quality Tracker
QvQ-72B-Preview Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Tue Sep 22 2026Try now
huggleMake it with
QvQ-72B-Preview.
QvQ-72B-Preview latency
QvQ-72B-Preview time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
QvQ-72B-Preview examples
Recent arena outputs from QvQ-72B-Preview, picked from the highest-ranked matchups.
QvQ-72B-Preview license
QvQ-72B-Preview is a proprietary model available under its provider's product and API terms, has 73.4B parameters.
- License
- Qwen
- Hosted access
- Parameters
- 73.4B
Alibaba Qwen License
QvQ-72B-Preview resources
Official sources for QvQ-72B-Preview: provider documentation, official launch post, source repository.
QvQ-72B-Preview vs other models
The most-compared alternatives to QvQ-72B-Preview are Kimi-k1.5, o1, Pixtral Large. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like QvQ-72B-Preview
Models ranked just above and below QvQ-72B-Preview by LLM Stats score.
FAQ
Common questions about QvQ-72B-Preview.