Creator
Alibaba
Released
2024-06-07
Intelligence
6.0
Artificial Analysis Index
Coding
—
Artificial Analysis Index
In $/1M
$0.00
input tokens
Out $/1M
$0.00
output tokens
Blended $/1M
$0.00
3:1 blended
Speed
0
tokens / sec
Profile
License, openness, and modality — the governance layer.
License
tongyi-qianwen
non-commercial
Weights
Open
downloadable
Modalities
—
Parameters
72B
total
Qwen2-72B-Instruct is an instruction-tuned language model with 72 billion parameters, supporting a context length of up to 131,072 tokens. It's part of the new Qwen2 series, which has surpassed most open-source models and demonstrates competitiveness against proprietary models across various benchmarks.
Capability profile
Category strength across 20 domains, via LLM Stats.
code
80language
80math
70legal
70general
70reasoning
70
healthcare
70finance
60biology
40physics
40chemistry
40
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
37
Humanity’s Last Exam
4
MMLU-Pro
62
SciCode
23
LiveCodeBench
16
MATH-500
70
AIME 2025—
τ²-Bench (agentic)—
Terminal-Bench Hard—
IFBench—