HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

glm-4-9b

zai-org/glm-4-9b

kind
original
quant
bf16 (16-bit)
family
glm
modality
text-generation
root model
zai-org/glm-4-9b
provider
zai-org
license
other
language
zh, en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
13,183
likes
144
created
—
last modified
2025-04-22T09:45:02+00:00 (2025)
huggingface
https://huggingface.co/zai-org/glm-4-9b
tags
transformerssafetensorschatglmglmthudmtext-generationcustom_codezhenarxiv:2406.12793license:othereval-resultsregion:us

Benchmark scores (6)

benchmarkcategoryscorecontextconfevidence
GSM8Kmath84.0high| GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** |
C-Evalknowledge77.1high| GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** |
MMLUknowledge74.7high| GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** |
HumanEvalcoding70.1high| GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** |
GPQAreasoning34.3high| GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** |
MATHmath30.4high| GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.