Qwen3 VL 8B Instruct: benchmarks, price and rank
Qwen3 VL 8B Instruct from Alibaba is 122nd of 123 rated AI models on Spezia's leaderboard. It costs $0.08 in, $0.50 out per million tokens.
- 122nd of 123 rated models
- Rating 171
- Rated on 5 benchmarks
- Open weights
- Released Sep 22, 2025
- 262,000 tokens of context
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 18th of 18 on ScreenSpot-Pro
- 43rd of 45 on CharXiv Reasoning
- 20th of 21 on ERQA
Price: $0.08 in, $0.50 out per million tokens.
Its headline results
The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.
- LiveCodeBench v658.6%
Programming contest problems collected after models were trained, from LeetCode, AtCoder and Codeforces.
37th of 43. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- MMMU-Pro60.4%
College exam questions that need a picture to answer, such as charts, diagrams, maps and chemical structures, with more answer options than the original MMMU and some questions shown only as a screenshot.
47th of 51. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- CharXiv Reasoning53%
Questions about real charts from scientific papers that need reasoning across the chart, not just reading off a value.
43rd of 45. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- ScreenSpot-Pro54.6%
Screenshots of professional software at full resolution, with an instruction to find the exact button or field to use.
18th of 18. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- ERQA46.8%
400 questions about images of the physical world: space, motion, actions, the state of objects and views from several cameras.
20th of 21. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- MMLU-Pro77.3%
Twelve thousand multiple-choice questions across fourteen subjects, from law and medicine to engineering, with ten options each.
47th of 56. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
2 more results in its full profile.
Every result with its source, what it costs per task, what jumped with its release, side by side with any other model, and answers to your questions about when to use it.
Models ranked near it
How the rating works, and every benchmark it uses: the model leaderboard.