0

GLM 4.7

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

Publisher
Zai
Family
Glm
Context
205K
Input
Output
License
mit
Released
22 Dec 2025

Cite

Notes

Only stored in your browser.

Attribution

Benchmark scores
frontiermathAAprime-hubLiveBenchVals AIEQ-Bench
Attribution policy →
Context
205K
Weights
Open
downloadable
Input
$0.60
/1M tok
Output
$2.20
/1M tok
Blended
$1
#376/ 493/1M · 3:1
Speed
0
#103/ 492tok/s
Cache read
$0.11
0.18x input

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

Reasoning effortIndexSpeed
Reasoning22.20 t/s
Non-reasoning17.40 t/s

Intelligence Index per reasoning-effort setting, via Artificial Analysis · pricing identical across tiers

Reported on 30 evals across 11 domains - best 100.0% on Nsa Codebreaker · #1 of 4

Reported eval scores

30
Nsa Codebreaker100
Deepdive46.7
Medpt33.3
GSM8K90
FrontierMath2.4
LiveCodeBench89.4
AIME 2025: Problems from the American Invitational Mathematics Examination95
ProofBench6
τ²-bench (Tau²-bench)95.9
MMLU-Pro85.6
Humanity's Last Exam (HLE)27.4
LiveBench60.8
GPQA Diamond85.9
SciCode45.1
IFBench67.9
LiveBench - Coding73.1
Terminal-Bench (Hard)31.8
LiveBench - Language65.2
LiveBench - Data Analysis55.2
LiveBench - Math76

Head-to-heads

29

benchmark comparisons against other models

vs Claude Sonnet 4.525 shared evalsvs GPT-5 Mini25 shared evalsvs Claude Opus 4.525 shared evalsvs GPT-5.224 shared evalsvs Grok 4.1 Fast24 shared evalsvs GPT-5 Nano23 shared evalsvs GPT-5.522 shared evalsvs Claude 4 Sonnet22 shared evalsvs GLM 5.122 shared evalsvs DeepSeek V3.222 shared evalsvs Gemini 3.1 Pro Preview21 shared evalsvs Claude Opus 4.821 shared evalsvs Claude Opus 4.621 shared evalsvs GPT-5.421 shared evalsvs Claude Opus 4.721 shared evalsvs Claude Fable 520 shared evalsvs Kimi K2.520 shared evalsvs Gemini 2.5 Pro20 shared evalsvs gpt-oss-120b20 shared evalsvs Claude Sonnet 4.619 shared evalsvs GPT-5.4 Mini19 shared evalsvs Qwen3.6 Plus18 shared evalsvs GPT-517 shared evalsvs GPT-4o16 shared evalsvs GPT-4.1 Mini14 shared evalsvs GPT-4o-mini14 shared evalsvs GPT-4.1 Nano14 shared evalsvs GPT-4.113 shared evalsvs GPT-6 Astra9 shared evals