0

GLM 4.7

Open weights

GLM-4.7 is an AI model from Zai, released with open weights.

Publisher
Zai
Family
Glm
Context
203K
Input
Output
License
mit
Released
22 Dec 2025

Cite

Notes

Only stored in your browser.

Attribution

Benchmark scores
frontiermathAAprime-hubLiveBenchVals AI
Attribution policy →
Context
203K
Input
$0.60
/1M tok
Output
$2.20
/1M tok
Blended
$1
#307/ 414/1M · 3:1
Speed
84
#131/ 414tok/s
Cache read
$0.08
0.13x input

Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter

Reported on 28 evals across 10 domains - best 100.0% on Nsa Codebreaker · #1 of 4

Reported eval scores

28
Nsa Codebreaker100
Deepdive46.7
Medpt33.3
GSM8K90
FrontierMath2.4
τ²-bench (Tau²-bench)94.2
Terminal-Bench (Hard)30.3
LiveBench - Coding73.1
IFBench54.6
LiveBench - Language65.2
LiveBench - Data Analysis55.2
LiveBench - Math76
LiveBench - Reasoning59.7
LiveBench - Instruction Following35.7
MMLU-Pro79.4
LiveBench60.8
Humanity's Last Exam (HLE)6.1
LiveCodeBench56.2
SciCode35.4
GPQA Diamond66.4
AIME 2025: Problems from the American Invitational Mathematics Examination48
ProofBench6
TaxEval v268.8
CorpFin v246.4
MedCode32.8
MedScribe68.6