← Back to all models
Q

Qwen3 Coder 30B

by Alibaba
Flagship Free & Open Source 🏆 Ranked #42 of 85
75.2
Overall Score
out of 100
About

Alibaba's code-specialised 30B model from the Qwen3 series, with expertise across major programming languages and agentic coding workflows. Leads open-source coding benchmarks at its parameter class.

Key Metrics
Context Window
128K
tokens
Avg Response
800
milliseconds
Input Cost
$0.2
per million tokens
Output Cost
$0.6
per million tokens
Arena ELO
1240
Chatbot Arena rating
MT-Bench
8.7
out of 10
Benchmark Scores
MMLU
78.0%
HumanEval
93.0%
MATH
82.0%
GPQA
44.0%
MT-Bench
87.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ Code generation ✓ Multi-language support ✓ Agentic coding ✓ Open source ✓ Strong debugging
Limitations
⚠ Coding-specialised ⚠ Less general-purpose ⚠ Requires 20GB+ VRAM
Ideal Use Cases
Code generation Debugging Code review Software engineering Agentic coding
Model Details
Provider Alibaba
Released 2025-05-01
Type Free & Open Source
Multimodal No
Tier Flagship
Global rank #42 / 85
Pricing (USD)
Input tokens $0.2/M
Output tokens $0.6/M
Per 1,000 tokens ≈ $0.0002 input / $0.0006 output
All Benchmarks
MMLU 78.0%
HumanEval 93.0%
MATH 82.0%
GPQA 44.0%
MT-Bench 8.7/10
Arena ELO 1240
Compare this model View Rankings

You might also consider