Skip to content
aiqbench

Zai · model passport

Z.ai: GLM 5.2

glm-5-2
  • Open weights
  • MIT licence
  • 753.3B params
  • 1,048,576 context
  • Released 2026-06-16(HF repo created)
15/27axes covered
Overall · LMArena
1,476#28 of 396
Best percentile
93.2Overall
Cohort standing
72.8median 59.6

What the data says

Benchmarked on 15 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 93.2 pct — Overall (1,476)
  • 91.9 pct — Instruction following (1,470)
  • 91.4 pct — Hard prompts (1,496)

Uneven: 59.1 percentile points between its best and worst axis — 93.2 pct on Overall versus 34.1 pct on SimpleQA Verified.

  • Overall93.2 pct1,476Verify →
  • Instruction following91.9 pct1,470Verify →
  • Hard prompts91.4 pct1,496Verify →
  • GPQA Diamond89.1 pct91.9%Verify →
  • LiveBench89 pct73.2%Verify →
  • Coding89 pct1,513Verify →
  • IFBench (Artificial Analysis)88.9 pct73.3%Verify →
  • SWE-bench Verified87.5 pct78.7%Verify →
  • WebDev Arena82.7 pct1,605Verify →
  • Factuality Arena79.1 pct1,463Verify →
  • SimpleBench67.8 pct58.8%Verify →
  • AIME (math)64 pct86.4%Verify →
  • Agent Arena60 pct0.024Verify →
  • ARC-AGI-252.8 pct22.8%Verify →
  • SimpleQA Verified34.1 pct34.2%Verify →
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • FrontierMathNot benchmarked
  • Humanity's Last ExamNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not 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-5.2
Parameters753.3B
ArchitectureGlmMoeDsaForCausalLM
LicenceMIT

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "zai-org/GLM-5.2"
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-5.2
Context length1,048,576 tokens
Max output943,718 tokens
Input price$0.62 per 1M tokens
Cached input price$0.14 per 1M tokens
Output price$2.42 per 1M tokens

API parameters this endpoint supports

Frequency penaltyInclude reasoningLogit biasLogprobsMax tokensMin-pParallel Tool CallsPresence penaltyReasoningReasoning effortRepetition penaltyResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-kTop logprobsTop-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-5.2","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-5.2-max stands at 72.8 (raw mean 77.4) — measured on 15 of 27 axes.

    standingtemplateVerify →

  • glm-5.2-max stands at 72.8 versus a cohort median of 59.6 across 205 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 →