Great multilingual support, strong at mathematics and coding, supports roleplay and chatbots.
Added Jul 3, 2025
Model weightsContext Window
131.1K
Max Output
8.2K
Input Price (Auto)
$0.37/1M
Output Price (Auto)
$0.43/1M
Cache Read (Auto)
$0.19/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
10.2
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
58.7%
Better than 39% of models compared
HLE
Humanity's Last Exam
4.5%
Better than 24% of models compared
IFBench
Instruction-following benchmark
36.9%
Better than 32% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
34.5%
Better than 43% of models compared
AA-LCR
Long context reasoning evaluation
20.0%
Better than 34% of models compared
CritPt
Research-level physics reasoning
0.0%
Coding
SciCode
Python programming for scientific computing
33.7%
Better than 54% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
4.5%
Better than 28% of models compared
LiveCodeBench
Contamination-free coding benchmark
35.9%
Better than 43% of models compared
Math
AIME
American Invitational Mathematics Examination
23.3%
Better than 50% of models compared
Math-500
Diverse mathematical problem solving benchmark
83.5%
Better than 50% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
76.2%
Better than 53% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
17.5%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
85.5%
Last updated Jun 28, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare Qwen2.5 72B with similar models from the same provider or model family.
Qwen 2.5 Coder 32b
Qwen/Qwen2.5-Coder-32B-InstructThe latest series of Code-Specific Qwen large language models.
Qwen3 Next 80B A3B (Instruct)
Qwen/Qwen3-Next-80B-A3B-InstructBased on the new Qwen3‑Next architecture (hybrid attention, highly sparse MoE, training‑stability optimizations, and multi‑token prediction), the Qwen3‑Next‑80B‑A3B‑Instruct model delivers extreme efficiency with only 3B active parameters per pass. It performs comparably to Qwen3‑235B‑A22B‑Instruct‑2507 and shows clear advantages on ultra‑long context tasks (up to 256K tokens).
Qwen 3 235b A22B 2507
Qwen/Qwen3-235B-A22B-Instruct-2507Qwen 3 235b A22B Instruct 2507 the updated version of Qwen3 235B A22B, with significant improvements in performance. This model is non-thinking.
Qwen3 VL 235B A22B Instruct
Qwen/Qwen3-VL-235B-A22B-InstructQwen3 Vision‑Language model (235B MoE, ≈22B active) tuned for instruction following and grounded visual QA. Excels at image understanding, dense OCR, charts/diagrams, and multi‑image context.
Qwen3.6 35B A3B Thinking
Qwen/Qwen3.6-35B-A3B:thinkingQwen3.6 35B A3B is a native vision-language MoE model with hybrid attention. Compared to Qwen3.5 35B A3B, Alibaba reports stronger agentic coding, mathematical and code reasoning, and better spatial understanding (including object localization and detection).
Qwen3.6 35B A3B
Qwen/Qwen3.6-35B-A3BQwen3.6 35B A3B is a native vision-language MoE model with hybrid attention. Compared to Qwen3.5 35B A3B, Alibaba reports stronger agentic coding, mathematical and code reasoning, and better spatial understanding (including object localization and detection).