Skip to content
aiqbench

Zai · model passport

Z.ai: GLM 4.5V

glm-4-5v
  • Open weights
  • MIT licence
  • 107.7B params
  • 65,536 context
  • Released 2025-08-11(curated)
8/27axes covered
Overall · LMArena
1,352#198 of 396
Best percentile
63.4LiveCodeBench (Artificial Analysis)
Cohort standing
48.7median 52.0

What the data says

Benchmarked on 8 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 37.2 percentile points between its best and worst axis — 63.4 pct on LiveCodeBench (Artificial Analysis) versus 26.2 pct on IFBench (Artificial Analysis).

  • LiveCodeBench (Artificial Analysis)63.4 pct60.4%Verify →
  • MMLU-Pro (Artificial Analysis)62.2 pct78.8%Verify →
  • Hard prompts51.5 pct1,373Verify →
  • Coding51.2 pct1,403Verify →
  • Overall50.3 pct1,352Verify →
  • Instruction following49.5 pct1,338Verify →
  • Vision Arena32 pct1,153Verify →
  • IFBench (Artificial Analysis)26.2 pct34.2%Verify →
  • WebDev ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Run it yourself

Repositoryzai-org/GLM-4.5V
Parameters107.7B
ArchitectureGlm4vMoeForConditionalGeneration
LicenceMIT

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "zai-org/GLM-4.5V"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Use it hosted

API model IDz-ai/glm-4.5v
Context length65,536 tokens
Max output16,384 tokens
Acceptstext, image
Input price$0.60 per 1M tokens
Cached input price$0.11 per 1M tokens
Output price$1.80 per 1M tokens

API parameters this endpoint supports

Frequency penaltyInclude reasoningMax tokensPresence penaltyReasoningRepetition penaltyResponse formatSeedStop sequencesTemperatureTool choiceTool callingTop-kTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"z-ai/glm-4.5v","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • glm-4.5v stands at 48.7 (raw mean 48.3) — measured on 8 of 27 axes.

    standingtemplateVerify →

  • glm-4.5v stands at 48.7 versus a cohort median of 52 across 145 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →