HF Model & Benchmark Matrix

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

GLM-4.7-Flash

unsloth/GLM-4.7-Flash

kind
original
quant
bf16 (16-bit)
family
glm
modality
text-generation
root model
zai-org/GLM-4.7-Flash
provider
unsloth
license
mit
language
en, zh
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
302,619
likes
15
created
—
last modified
2026-02-12T18:52:25+00:00 (2026)
huggingface
https://huggingface.co/unsloth/GLM-4.7-Flash
tags
transformerssafetensorsglm4_moe_litetext-generationunslothconversationalenzharxiv:2508.06471base_model:zai-org/GLM-4.7-Flashbase_model:finetune:zai-org/GLM-4.7-Flashlicense:mitendpoints_compatibleregion:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
GPQAreasoning75.2GPQAmedium| GPQA | 75.2 | 73.4 | 71.5 |
SWE-bench Verifiedswe59.2SWE-bench Verifiedmedium| SWE-bench Verified | 59.2 | 22.0 | 34.0 |
BrowseCompagentic42.8BrowseCompmedium| BrowseComp | 42.8 | 2.29 | 28.3 |
Humanity's Last Examknowledge14.4HLEmedium| HLE | 14.4 | 9.8 | 10.9 |

Discussions (0)

none scraped.

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