Better than 52% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text-generation
License
Open Source
Benchmarks
6 tested
Data updated today
About
Qwen text generation model. 1217K downloads on HuggingFace.
Tested on 6 benchmarks with 60.6% average. Top scores: OpenCompass — IFEval (88.5%), OpenCompass — AIME2025 (80.0%), OpenCompass — MMLU-Pro (72.8%).
Capabilities
coding
51.6
#62 globally
math
80.0
#19 globally
knowledge
47.8
#110 globally
language
88.5
#18 globally
Benchmark Scores
Compare AllTested on 6 benchmarks · Ranked across 4 categories
Score Distribution (all 231 models)
0255075100
▲ You are here
codingCompare coding →
OpenCompass — LiveCodeBenchV6
51.6—OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.
mathCompare math →
OpenCompass — AIME2025
80.0—OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.
knowledgeCompare knowledge →
OpenCompass — MMLU-Pro
72.8—OpenCompass MMLU-Pro evaluation. Harder knowledge test with more answer choices.
OpenCompass — GPQA-Diamond
64.7—OpenCompass evaluation of GPQA Diamond. PhD-level science questions from the hardest subset.
OpenCompass — HLE
6.0—OpenCompass evaluation of Humanitys Last Exam. Expert-level cross-discipline knowledge test.
vs R1
vs Phi 4 Mini Instruct
vs Mistral 7B V0.1 Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Info
Research
Documentation
Community
Source Code
BenchGecko API
qwen-qwen3-4b-thinking-2507
Specifications
- Typetext-generation
- ContextN/A
- ReleasedAug 2025
- LicenseOpen Source
- StatusActive
Available On
AlibabaTBDLearn More
Share & Export
Frequently Asked Questions
Qwen3 4B Thinking 2507 is an open-source text-generation AI model by Alibaba, released in August 2025. It has an average benchmark score of 48.4.