MDL
GLM-4.5-Air
Z AI
Verified against Artificial Analysis · Jul 27, 2026
Capability
67
percentile index
Price /M
$0.17 / $0.98
in / out
Context
131.1K
tokens
Avg score
53.3
11 benchmarks
AA Intelligence
16.5
index
Weights
Open
Released
Jul 28, 2025
About
GLM-4.5-Air is a open-weights model in the GLM family from Z AI. Benchmarked on 11 evals, averaging 53.3.
Benchmark scores · 11
avg 53.3 — higher is betterThe research behind this model
all papers mentioning it →What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness▲ 14 on HF · Jul 9, 2026GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models2 cites · Aug 8, 2025
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Price in / out$0.17 / $0.98 per 1M
Blended price$0.372 / 1M
Math index80.7
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$0.98/M