← Back to all models
Q

Qwen 2.5 14B

by Alibaba
Efficient Free & Open Source 🏆 Ranked #49 of 85
72.6
Overall Score
out of 100
About

Alibaba's mid-size 14B model from the Qwen 2.5 series. Strikes an excellent balance between capability and compute requirements, outperforming many larger models on maths and coding benchmarks.

Key Metrics
Context Window
128K
tokens
Avg Response
620
milliseconds
Input Cost
$0.14
per million tokens
Output Cost
$0.28
per million tokens
Arena ELO
1210
Chatbot Arena rating
MT-Bench
8.6
out of 10
Benchmark Scores
MMLU
79.5%
HumanEval
86.0%
MATH
83.0%
GPQA
42.0%
MT-Bench
86.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ Strong maths and coding ✓ Good size-to-quality ratio ✓ Open source ✓ Large context ✓ Multilingual
Limitations
⚠ Requires 16GB+ VRAM ⚠ Less general than 72B ⚠ Fewer integrations
Ideal Use Cases
Research Code assistance Mathematical problem solving Document analysis Multilingual tasks
Model Details
Provider Alibaba
Released 2024-09-18
Type Free & Open Source
Multimodal No
Tier Efficient
Global rank #49 / 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 79.5%
HumanEval 86.0%
MATH 83.0%
GPQA 42.0%
MT-Bench 8.6/10
Arena ELO 1210
Compare this model View Rankings

You might also consider