Skip to content
llmwaves

GLM 4.5V

Z.ai · released Aug 11, 2025

Open weightsReasoningTool useStructured outputVision

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

Specification

Context window
66K
Max output
16K
Knowledge cutoff
Dec 31, 2024
Parameters
107.7B
Licence
mit
Serving providers
2
Moderated
No

Intelligence

6.8

23th percentile

Coding

Coding Index

Agentic

Agentic Index

Output speed

42 t/s

Median across providers

Latency

2.01s

Time to first token

Cost per task

$0.17

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

  • MMLU-Pro
    75.1%
  • GPQA Diamond
    57.3%
  • LiveCodeBench
    35.2%
  • IFBench
    28.6%
  • τ²-bench (Telecom)
    19.6%
  • SciCode
    18.8%
  • AIME 2025
    15.3%
  • Terminal-Bench Hard
    6.8%
  • Humanity's Last Exam
    3.5%
  • AA-LCR (long context)
    0.0%

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

View as table
EvaluationScore
MMLU-Pro75.1%
GPQA Diamond57.3%
LiveCodeBench35.2%
IFBench28.6%
τ²-bench (Telecom)19.6%
SciCode18.8%
AIME 202515.3%
Terminal-Bench Hard6.8%
Humanity's Last Exam3.5%
AA-LCR (long context)0.0%

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
Mistral Large 24077.0
Qwen2.5 Coder 32B Instruct6.9
GLM 4.5V6.8
GPT-46.8
Gemini 2.5 Flash Lite6.7
GPT-4o-mini6.7
GPT-4o-mini (2024-07-18)6.7
Granite 4.1 8B6.4

Percentile among all indexed models

Intelligence23th
Mathematics19th
Terminal work35th

Pricing

What it costs to run

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

List price

Input / 1M tokens
$0.6
Output / 1M tokens
$1.8
Cached input / 1M
$0.11
Blended 3:1
$0.9

One task, estimated

$0.17

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.