Skip to content
aiqbench

Zai · model passport

Z.ai: GLM 4.6V

glm-4-6v
  • Open weights
  • MIT licence
  • 107.7B params
  • 131,072 context
  • Released 2025-12-07(HF repo created)
10/27axes covered
Overall · LMArena
1,378#176 of 396
Best percentile
66.7MMLU-Pro (Artificial Analysis)
Cohort standing
45.3median 54.9

What the data says

Benchmarked on 10 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 14.5 pct — Factuality Arena (1,391)

Uneven: 52.2 percentile points between its best and worst axis — 66.7 pct on MMLU-Pro (Artificial Analysis) versus 14.5 pct on Factuality Arena.

  • MMLU-Pro (Artificial Analysis)66.7 pct79.9%Verify →
  • Instruction following56.3 pct1,367Verify →
  • Overall55.8 pct1,378Verify →
  • Coding54 pct1,416Verify →
  • Hard prompts53.5 pct1,384Verify →
  • LiveCodeBench (Artificial Analysis)50.8 pct41.1%Verify →
  • Vision Arena36.7 pct1,161Verify →
  • LiveBench34 pct45.4%Verify →
  • IFBench (Artificial Analysis)16.4 pct30.1%Verify →
  • Factuality Arena14.5 pct1,391Verify →
  • WebDev 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
  • 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-4.6V
Parameters107.7B
ArchitectureGlm4vMoeForConditionalGeneration
LicenceMIT

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "zai-org/GLM-4.6V"
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-4.6v
Context length131,072 tokens
Max output32,768 tokens
Acceptsimage, text, video
Input price$0.30 per 1M tokens
Cached input price$0.06 per 1M tokens
Output price$0.90 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-4.6v","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-4.6v stands at 45.3 (raw mean 43.9) — measured on 10 of 27 axes.

    standingtemplateVerify →

  • glm-4.6v stands at 45.3 versus a cohort median of 54.9 across 123 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 →