whatmodel.sh / GLM-4.5V

GLM-4.5V

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

GLM-4.5V is an open-weights language model from Z.ai, released August 2025. Its published size is 106B parameters (12B active per token) and a 64k-token context window. Licence: mit.

Catalogue identity notes

Arena entry 'glm-4.5v' (text, vision). Maker repo zai-org/GLM-4.5V @ed47433: licence tag mit. Parameters: card: 'based on ... GLM-4.5-Air (106B parameters, 12B active)'. Released 2025-08: card news: '2025/08/11: We released GLM-4.5V'.

61.2±1.6#184 of 719 LLMsfrom 12 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of GLM-4.5V, out of 828 with a score, then more from Z.ai.

#modelscorewhereRAMreleased
217MiniMax-M1 (40k) MiniMax61±1comparison only2025-06
218Grok 4 Fast SpaceXAI (xAI)61±2comparison only2025-09
219GLM-4.5V Z.ai61±2api $0.90/M +local~69GB2025-08
220Llama 3.1 Nemotron Ultra 253B v1 NVIDIA61±2local~82GB2025-04
221HyperCLOVA X SEED 32B Think NAVER Cloud61±2comparison only2025-12
more from Z.ai
33GLM-5.3 Z.ai76±1api $2.15/M +local~239GB2026-08
52GLM-5.3-Flash Z.ai74±1api $0.24/M +local~103GB2026-08
57GLM-5.2 Z.ai74±1api $2.15/M +local~121GB2026-06

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #155 of 393 * · 22% of its score · 1 test

Beats MiniMax-M2, MiniCPM5 2B, Granite 4.2 30B here, though they rank higher overall. Trails LFM2.5 1.2B Thinking, LFM2.5 8B-A1B, LFM2.5 2.6B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1352.4 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 197/379avg 1268▇▇▇▇▇▇▇▇▇ 22%blunt
vision & documents▁▁▃▂▁▃▄▃▆▇█▄ #90 of 147 · 68% of its score · 8 tests

Beats DeepSeek V4 Flash Vision (Exp), GPT-5 nano here, though they rank higher overall. Trails Mistral Small 4 (119B-A6.5B), Qwen3-VL 32B Instruct, GPT-4.1 mini here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
CharXiv (reasoning questions) +163.0% ✎▄·····▄▄·▄·█ beats 3/5medium · avg 38%▇▇▇▇▇▇ 16%at its level · small run · several runs
Arena vision (style controlled)1152.7 ✎▁▁▂▂▂▂▄▅▅▆██ beats 49/145avg 1068▇▇▇▇▇▇ 15%blunt
ChartArena chart parsing (English, mAP_high average)43.8% ✎▁·▁·▃▃▁▇▃█·▄ beats 14/22hard · avg 27%▇▇▇▇▇ 12%blunt · at its level
MMMU (val) lab75.4% ✎▁····▁▁▄█▇▆▆ beats 38/52medium · avg 58%▇▇▇ 7.1%at its level · small run
MMMU Pro lab65.2% ✎▂▃▁▃▆▇▃▇▇██▅ beats 24/52medium · avg 46%▇▇▇ 6.7%at its level · small run
MMStar lab75.3% ✎▃▅▂▃▂▂▆█▆▆█▅ beats 20/34medium · avg 63%▇▇ 5.2%at its level · small run
CharXiv descriptive questions90.8% ✎▄····▄···█▄▄ beats 3/5easy · avg 68%▇▇ 4.8%noisy
OCRBench lab86.5% ✎▁·▃▁▆▅▂█▅█▁▃ beats 20/37easy · avg 83%▇ 1.6%blunt · small run
other tests2 not in a task · 8.9% of its score
testresultvs the others in its rundifficultycountswhy
LVBench lab53.8% ✎▇·█▅▅▄▄··▃▁▁ beats 6/28hard · avg 49%▇▇ 4.7%at its level · small run
AndroidWorld lab57.0% ✎▁·▁▁▂▃█▅▂▂·▂ beats 10/24medium · avg 41%▇▇ 4.2%blunt · at its level · small run

$ where to run it

Through an API

api · $0.90/M · $0.6 in / $1.8 out per 1M tokens · 64k context · docs.z.ai ↗ · price sourceUSD per 1M tokens, Z.ai API pricing page, Vision Models table, GLM-4.5V: input $0.6, output $1.8; cached input $0.11 excluded. Currency: USD. Z.ai official pricing page, observed 2026-09-28.

llama.cpp · recommended

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run GLM-4.5V · needs ~64.63 GB · from huggingface.co/ggml-org
    chat in the terminal
    llama cli -hf ggml-org/GLM-4.5V-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf ggml-org/GLM-4.5V-GGUF:Q4_K_M

LM Studio

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run GLM-4.5V · needs ~64.63 GB · from huggingface.co/ggml-org

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/ggml-org/GLM-4.5V-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Weights and documentation: huggingface.co/zai-org ↗

$ how the score was worked out · Z.ai GLM-V GitHub repository… 37%, LMArena leaderboard dataset 37%, ServiceNow-AI/Apriel-1.6-15b-… 13% and 1 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Z.ai GLM-V GitHub repository benchmark image (GLM-4.6V) · lab-reported7▇▇▇▇▇▇▇▇▇▇▇ 37%Apache-2.0
LMArena leaderboard dataset2▇▇▇▇▇▇▇▇▇▇▇ 37%CC BY 4.0
ServiceNow-AI/Apriel-1.6-15b-Thinker model card2▇▇▇▇ 13%MIT
ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)1▇▇▇▇ 12%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 61.2

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json