Qwen2 7B Instruct
Alibaba Cloud / Qwen TeamQwenOpen WeightApache 2.0 · Commercial OK
Description
Qwen2-7B-Instruct is an instruction-tuned language model with 7 billion parameters, supporting a context length of up to 131,072 tokens.
Release Date
2024-07-23
Parameters
7.6B
Context Length
—
Modalities
—
Capability Radar
60
general
60
coding
60
reasoning
26
scienceest.
60
agents
0
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
No ranking data available
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Chat
MT-Bench
0.84 / 100SR
General
C-Eval
77.2%SR
AlignBench
72.1%SR
MMLU
70.5%SR
MultiPL-E
59.1%SR
Language
MMLU-Pro
44.1%SR
Math
GSM8k
82.3%SR
MATH
49.6%SR
TheoremQA
25.3%SR
Reasoning
HumanEvalOpenAI (2021)
79.9%SR
EvalPlus
0.70 / 100SR
MBPP
0.67 / 100SR
LiveCodeBench
26.6%SR
GPQANYU + Cohere + Anthropic (2023)
25.3%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Chat80
Roleplay80
Communication80
Creativity80
Writing70
Language60
Legal60
Math60
Reasoning60
General60
Healthcare60
Code60
Finance50
Physics30
Biology30
Chemistry30
Pricing
No pricing data available
Speed
No speed data available
Provider Price Ranking
No provider data available