Skip to content
aiqbench

Zai · model passport

Z.ai: GLM 4.5

glm-4-5
  • Open weights
  • MIT licence
  • 358.3B params
  • 131,072 context
  • Released 2025-07-28(curated)
9/27axes covered
Overall · LMArena
1,411#137 of 396
Best percentile
85.0MMLU-Pro (Artificial Analysis)
Cohort standing
61.8median 51.6

What the data says

Benchmarked on 9 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 85 pct — MMLU-Pro (Artificial Analysis) (83.5%)

Uneven: 50.2 percentile points between its best and worst axis — 85 pct on MMLU-Pro (Artificial Analysis) versus 34.8 pct on Humanity's Last Exam.

  • MMLU-Pro (Artificial Analysis)85 pct83.5%Verify →
  • LiveCodeBench (Artificial Analysis)83.2 pct73.8%Verify →
  • LiveBench72.5 pct65.0%Verify →
  • Instruction following68.4 pct1,404Verify →
  • Hard prompts67.7 pct1,433Verify →
  • Overall65.7 pct1,411Verify →
  • Coding65 pct1,455Verify →
  • IFBench (Artificial Analysis)49.4 pct44.1%Verify →
  • Humanity's Last Exam34.8 pct8.3%Verify →
  • WebDev ArenaNot benchmarked
  • Vision 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
  • SimpleBenchNot 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-4.5
Parameters358.3B
ArchitectureGlm4MoeForCausalLM
LicenceMIT

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "zai-org/GLM-4.5"
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-4.5
Context length131,072 tokens
Max output98,304 tokens
Input price$0.60 per 1M tokens
Cached input price$0.11 per 1M tokens
Output price$2.20 per 1M tokens

API parameters this endpoint supports

Include reasoningMax tokensReasoningResponse formatTemperatureTool 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-4.5","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-4.5 stands at 61.8 (raw mean 65.7) — measured on 9 of 27 axes.

    standingtemplateVerify →

  • glm-4.5 stands at 61.8 versus a cohort median of 51.6 across 145 models released within 180 days — above 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 →