← Back to all models
Q

Qwen3 14B

by Alibaba
Efficient Free & Open Source 🏆 Ranked #38 of 85
76.3
Overall Score
out of 100
About

Alibaba's latest 14B model from the Qwen3 series featuring hybrid thinking mode. Supports seamless switching between deep reasoning and fast response, with state-of-the-art maths and coding for its size.

Key Metrics
Context Window
128K
tokens
Avg Response
680
milliseconds
Input Cost
$0.14
per million tokens
Output Cost
$0.28
per million tokens
Arena ELO
1230
Chatbot Arena rating
MT-Bench
8.8
out of 10
Benchmark Scores
MMLU
82.0%
HumanEval
87.0%
MATH
88.0%
GPQA
50.0%
MT-Bench
88.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ Hybrid thinking mode ✓ Excellent maths ✓ Strong coding ✓ Open source ✓ Multilingual
Limitations
⚠ Newer model ⚠ Less community testing ⚠ Thinking mode increases latency
Ideal Use Cases
Research Code generation Mathematical reasoning Multilingual tasks Agentic workflows
Model Details
Provider Alibaba
Released 2025-04-28
Type Free & Open Source
Multimodal No
Tier Efficient
Global rank #38 / 85
Pricing (USD)
Input tokens $0.14/M
Output tokens $0.28/M
Per 1,000 tokens ≈ $0.0001 input / $0.0003 output
All Benchmarks
MMLU 82.0%
HumanEval 87.0%
MATH 88.0%
GPQA 50.0%
MT-Bench 8.8/10
Arena ELO 1230
Compare this model View Rankings

You might also consider