Skip to content
aiqbench

Zai · model passport

Z.ai: GLM 5.1

glm-5-1
  • Open weights
  • MIT licence
  • 753.9B params
  • 204,800 context
  • Released 2026-04-03(HF repo created)
14/27axes covered
Overall · LMArena
1,465#48 of 396
Best percentile
94.1IFBench (Artificial Analysis)
Cohort standing
70.7median 62.7

What the data says

Benchmarked on 14 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 94.1 pct — IFBench (Artificial Analysis) (76.3%)
  • 89.6 pct — Instruction following (1,462)
  • 88.9 pct — Hard prompts (1,489)

Uneven: 61.2 percentile points between its best and worst axis — 94.1 pct on IFBench (Artificial Analysis) versus 32.9 pct on SimpleQA Verified.

  • IFBench (Artificial Analysis)94.1 pct76.3%Verify →
  • Instruction following89.6 pct1,462Verify →
  • Hard prompts88.9 pct1,489Verify →
  • Overall88.1 pct1,465Verify →
  • Coding88 pct1,512Verify →
  • LiveBench83.2 pct70.2%Verify →
  • GPQA Diamond81 pct89.9%Verify →
  • FrontierMath79.7 pct33.4%Verify →
  • AIME (math)77 pct93.3%Verify →
  • Factuality Arena73.3 pct1,456Verify →
  • WebDev Arena63.3 pct1,508Verify →
  • SimpleBench59.8 pct55.1%Verify →
  • SWE-bench Verified53.1 pct74.2%Verify →
  • SimpleQA Verified32.9 pct34.0%Verify →
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • ARC-AGI-2Not 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-5.1
Parameters753.9B
ArchitectureGlmMoeDsaForCausalLM
LicenceMIT

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "zai-org/GLM-5.1"
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-5.1
Context length204,800 tokens
Max output128,000 tokens
Input price$0.97 per 1M tokens
Cached input price$0.18 per 1M tokens
Output price$3.04 per 1M tokens

API parameters this endpoint supports

Frequency penaltyInclude reasoningLogit biasLogprobsMax tokensMin-pPresence penaltyReasoningRepetition 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-5.1","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-5.1 stands at 70.7 (raw mean 75.1) — measured on 14 of 27 axes.

    standingtemplateVerify →

  • glm-5.1 stands at 70.7 versus a cohort median of 62.7 across 116 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 →