MDL
GLM-5
Z AI
Verified against Artificial Analysis · Jul 13, 2026
Capability
90
percentile index
Price /M
$1 / $3.2
in / out
Context
202.8K
tokens
Avg score
61.8
7 benchmarks
AA Intelligence
39.5
index
Speed
51 tok/s
TTFT 0.8s
Released
Feb 11, 2026
About
GLM-5 is a open-weights model in the GLM family from Z AI. Benchmarked on 7 evals, averaging 61.8.
Benchmark scores · 7
avg 61.8 — higher is betterThe research behind this model
all papers mentioning it →VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models▲ 104 on HF · Jun 15, 2026K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts▲ 55 on HF · Jun 1, 2026SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories▲ 35 on HF · May 31, 2026Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning▲ 15 on HF · Jul 8, 2026ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions▲ 8 on HF · Jun 16, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed51 tok/s
Latency (TTFT)0.8s
First answer1m 2s
Price in / out$1 / $3.2 per 1M
Blended price$1.55 / 1M
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$3.2/M