Skip to content
aiqbench

Zai · model passport

Z.ai: GLM 4.7 Flash

glm-4-7-flash
  • Open weights
  • MIT licence
  • 31.2B params
  • 200,000 context
  • Released 2026-01-19(HF repo created)
9/27axes covered
Overall · LMArena
1,365#185 of 396
Best percentile
70.1IFBench (Artificial Analysis)
Cohort standing
48.7median 55.7

What the data says

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

Weakest axes

  • 8.1 pct — Factuality Arena (1,370)

Uneven: 62 percentile points between its best and worst axis — 70.1 pct on IFBench (Artificial Analysis) versus 8.1 pct on Factuality Arena.

  • IFBench (Artificial Analysis)70.1 pct60.8%Verify →
  • HHEM Hallucination (Vectara)56.2 pct90.7%Verify →
  • Coding55 pct1,423Verify →
  • Hard prompts53.8 pct1,384Verify →
  • Overall53.5 pct1,365Verify →
  • Instruction following52.5 pct1,348Verify →
  • AIME (math)43 pct58.3%Verify →
  • GPQA Diamond42.5 pct60.5%Verify →
  • Factuality Arena8.1 pct1,370Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot 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
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)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-4.7-Flash
Parameters31.2B
ArchitectureGlm4MoeLiteForCausalLM
LicenceMIT

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "zai-org/GLM-4.7-Flash"
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-4.7-flash
Context length200,000 tokens
Max output117,964 tokens
Input price$0.06 per 1M tokens
Output price$0.40 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-4.7-flash","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-4.7-flash stands at 48.7 (raw mean 48.3) — measured on 9 of 27 axes.

    standingtemplateVerify →

  • glm-4.7-flash stands at 48.7 versus a cohort median of 55.7 across 116 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 →