HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/Qwen/Qwen/Qwen-7B

Qwen/Qwen-7B

family qwen · 3 variants · unknown

provider
Qwen
released
—
huggingface
https://huggingface.co/Qwen/Qwen-7B
best scores
MMLU: 55.4C-Eval: 59.4GSM8K: 49.7MATH: 3.3HumanEval: 34.8MBPP: 20.8BBH: 38.2CMMLU: 31.8

Best scores per benchmark

benchmarkcategorybest score
C-Evalknowledge59.4
MMLUknowledge55.4
GSM8Kmath49.7
BBHreasoning38.2
HumanEvalcoding34.8
CMMLUknowledge31.8
MBPPcoding20.8
MATHmath3.3

Variants (3)

variantkindquantbitsvRAMdlorgyear
Qwen-7Boriginalbf1616.022,560Qwen2024
Qwen-7B-Chat-Int4gptqgptq463Qwen2024
Qwen-7B-Chat-Int8gptqgptq214Qwen2023
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.