Skip to content
llmwaves

GLM 5

Z.ai · released Feb 11, 2026

Open weightsReasoningTool useStructured output

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

Specification

Context window
205K
Max output
131K
Knowledge cutoff
Not stated
Parameters
753.9B
Licence
mit
Serving providers
12
Moderated
No
Uptime
100.0%

Intelligence

40.6

88th percentile

Coding

Coding Index

Agentic

Agentic Index

Output speed

48 t/s

Median across providers

Latency

937ms

Time to first token

Cost per task

$0.25

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • τ²-bench (Telecom)
    98.2%
  • GPQA Diamond
    82.0%
  • IFBench
    72.3%
  • AA-LCR (long context)
    70.7%
  • SciCode
    46.2%
  • Terminal-Bench Hard
    43.2%
  • Humanity's Last Exam
    29.3%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
τ²-bench (Telecom)98.2%
GPQA Diamond82.0%
IFBench72.3%
AA-LCR (long context)70.7%
SciCode46.2%
Terminal-Bench Hard43.2%
Humanity's Last Exam29.3%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
Inkling Small41.2
GPT-5.2-Codex41.2
Qwen3.6 Max Preview41.1
GLM 5.141.0
GPT-5.4 Mini40.9
GLM 540.6
Qwen3.6 Plus40.5
GPT-5.4 Nano39.7

Percentile among all indexed models

Intelligence88th
Terminal work90th
Arena Elo80th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.95
Output / 1M tokens
$2.55
Cached input / 1M
$0.2
Blended 3:1
$1.35

One task, estimated

$0.25

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.

Arena

Head-to-head generation quality

Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.

Overall Elo
1,284
Win rate
56.3%
Strongest at
3D scenes
Tournaments
9,245

Elo by category

Dot position on a 1,150–1,300 scale · Elo has no meaningful zero

Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.

View as table
CategoryEloWin rate
3D scenes128456.3%
Game development127557.4%
Websites127155.0%
UI components126653.6%
Data visualisation125653.0%
SVG121454.4%
Mobile apps119651.7%
Full-stack apps116351.7%