HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/THUDM/THUDM/glm-4-9b-chat

THUDM/glm-4-9b-chat

family glm · 2 variants · unknown

provider
THUDM
released
—
huggingface
https://huggingface.co/THUDM/glm-4-9b-chat
best scores
MT-Bench: 8.35IFEval: 69.0MMLU: 72.4C-Eval: 75.6GSM8K: 79.6MATH: 50.6HumanEval: 71.8MGSM: 54.0

Best scores per benchmark

benchmarkcategorybest score
GSM8Kmath79.6
C-Evalknowledge75.6
MMLUknowledge72.4
HumanEvalcoding71.8
IFEvalinstruction-following69.0
MGSMmath54.0
MATHmath50.6
MT-Benchchat8.35

Variants (2)

variantkindquantbitsvRAMdlorgyear
glm-4-9b-chat-hforiginalbf1616.021,735zai-org2025
glm-4-9b-chat-GGUFggufgguf2.05,810bartowski2024
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.