GLM-4.7 (Reasoning)
Z AIGLMOpen WeightMIT · Usage Commercial
Description
GLM 4.7 is a coding‑centric model that thinks before acting, preserves its reasoning across turns, and lets you control thinking per request for speed or accuracy. It upgrades agentic workflows with stronger multi‑step tool use, better terminal and multilingual coding, and a noticeable jump in UI output quality for modern, clean webpages and slides. You can use it in popular coding agents, call it via the Z.ai API, and even run it locally with public weights on HuggingFace and ModelScope using vLLM or SGLang.
Date de sortie
2025-12-22
Paramètres
358.0B
Longueur du contexte
205K
Modalités
text
Radar de capacités
42
general
62
coding
93
reasoning
68
science
60
agents
0
multimodal
Classements
| Domaine | #Rang | Score | Source |
|---|---|---|---|
| Classement codage | 199 | 67.0 | AA |
| Classement général | 92 | 68.0 | AA |
| Science | 152 | 66.0 | AA |
Scores de benchmarks (LLM Stats)
(LLM Stats (zeroeval))General
Tau-bench
87.4%Aut.
Language
MMLU-Pro
84.3%Aut.
Math
AIME 2025
95.7%Aut.
IMO-AnswerBench
82.0%Aut.
Reasoning
GPQANYU + Cohere + Anthropic (2023)
85.7%Aut.
LiveCodeBench v6
84.9%Aut.
SWE-Bench Verified
73.8%Aut.
SWE-bench Multilingual
66.7%Aut.
BrowseComp-zh
66.6%Aut.
BrowseCompOpenAI (2025)
52.0%Aut.
Humanity's Last Exam
42.8%Aut.
Terminal-Bench 2.0Stanford × Laude Institute (2026)
41.0%Aut.
Terminal-Bench
33.3%Aut.
Indices d'évaluation AA
(Artificial Analysis)Tau2(Sierra + U Toronto + Vector Institute (2025))95.9
Math Index(Artificial Analysis)95.0
Aime 25(MAA (Mathematical Association of America))95.0
Livecodebench(UC Berkeley + MIT + Cornell (2024))89.4
Gpqa(NYU + Cohere + Anthropic (2023))85.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))85.6
Lcr(Artificial Analysis)71.0
Ifbench(Google Research (2023))67.9
Terminalbench V2 145.3
Coding Index(Artificial Analysis)45.3
Terminalbench Hard(Stanford × Laude Institute (2026))31.8
Hle(Center for AI Safety + Scale AI (2025))27.4
Intelligence Index(Artificial Analysis)22.2
Tau Banking12.2
Scores par catégorie LLM Stats
(LLM Stats (zeroeval))Physics90
Biology90
Chemistry90
Language80
Legal80
Math80
Finance80
Healthcare80
Reasoning70
Frontend Development70
General70
Search60
Tool Calling60
Agents50
Code50
Vision40
Tarification
Prix d'entrée$0.6 / 1M tokens
Prix de sortie$2.2 / 1M tokens
Prix mixte (3:1)$1 / 1M tokens
Prix de lecture cache$0.11 / 1M tokens
Prix d'écriture cacheGratuit
Vitesse
Tokens/sec0.0
Délai du premier token0.00s
Temps de réponse0.00s
Classement des Prix par Fournisseur
Classement des Prix par Fournisseur
2 fournisseurs
Moins cher: DeepInfraPlus cher: Z AI
FournisseurEntréeSortie
1DeepInfraMoins cher
$0
$0
2Z AIPRINCIPAL
$0.6
$2.2
Comparer les prix entre différents fournisseurs API pour ce modèle.