Qwen2.5 14B Instruct
Alibaba Cloud / Qwen TeamQwenOpen WeightApache 2.0 · Commercial OK
Description
Qwen2.5-14B-Instruct is an instruction-tuned 14.7B parameter language model, part of the Qwen2.5 series. It features significant improvements in instruction following, long text generation (8K+ tokens), structured data understanding, and JSON output generation. The model supports a 128K token context length and multilingual capabilities across 29+ languages including Chinese, English, French, Spanish, and more.
Release Date
2024-09-19
Parameters
14.7B
Context Length
131K
Modalities
text
Capability Radar
70
general
80
coding
70
reasoning
43
scienceest.
73
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Reasoning | 91 | 51.0 | LS |
Benchmark Scores (LLM Stats)
Biology
GPQA
45.5%SR
Chemistry
MMLU-STEM
76.4%SR
Code
HumanEval
83.5%SR
Finance
MMLU
79.7%SR
MMLU-Pro
63.7%SR
TruthfulQA
58.4%SR
TheoremQA
43.0%SR
General
MBPP
0.82 / 100SR
MMLU-Redux
80.0%SR
MultiPL-E
72.8%SR
ARC-C
67.3%SR
MBPP+
63.2%SR
Language
BBH
78.2%SR
Math
GSM8k
94.8%SR
MATH
80.0%SR
Reasoning
HumanEval+
51.2%SR
AA Evaluation Indices
No AA evaluation data available
LLM Stats Category Scores
Code80
Language70
Legal70
Math70
Reasoning70
General70
Healthcare70
Finance60
Biology50
Chemistry50
Physics40
Pricing
Input Price$0.35 / 1M tokens
Output Price$1.4 / 1M tokens
Blended Price (3:1)$0.6125 / 1M tokens
Speed
No speed data available
Provider Price Ranking
Provider Price Ranking
5 providers
Cheapest: SiliconFlow (China)Most Expensive: Alibaba
ProviderInputOutput
1SiliconFlow (China)Cheapest
$0.1
$0.1
2SiliconFlow
$0.1
$0.1
3Alibaba (China)
$0.144
$0.431
4Alibaba Cloud / Qwen TeamPRIMARY
$0.35
$1.4
5Alibaba
$0.35
$1.4
Compare pricing across different API providers for this model.