ApertureAug 2026
FieldCompareLabsGuideMethod
  • Field
  • Compare
  • Labs
  • Guide
Z.ai (Zhipu)
Z

GLM-5.2

Jun 2026 · Open weight · Superseded · supported evidence

MIT-licensed predecessor. Faster than 5.3, less agentic. Keep it if the license is the feature.

Open compareLab site

Intelligence

52.6

AA Index

API price

$1.40 / $4.40

Input / output per 1M

Context

1M

141 tok/s

Capability

Intelligence Index52.6
Coding index68.8
Agentic index45.7
Arena Elo (offset)167

Use it when

  • ▸MIT license
  • ▸Fast GLM serving

Skip if

  • –You can take 5.3 for agents

Benchmarks

GPQA Diamond
Graduate-level science questions designed so Google search is not enough. Still one of the cleanest knowledge/reasoning splits.
—
Humanity’s Last Exam
Expert-written questions across fields. Harder than MMLU; the current differentiator for “does this model actually know things.”
—
MMLU-Pro
Harder, less-saturated successor to MMLU. Classic MMLU is above 90% for every flagship and no longer ranks the field.
—
SWE-bench Verified
500 human-validated GitHub issues. Score swings 5–15 points by harness — treat vendor numbers as an upper bound.
—
SWE-bench Pro
Harder, contamination-resistant coding eval. Currently the best public split between “can code” and “can maintain a repo.”
62.1%
Terminal-Bench 2.1
End-to-end tasks in a real terminal. Better proxy for coding agents than HumanEval, which is fully saturated.
—
ARC-AGI-2
Abstract visual puzzles. Rewards generalization over memorization. GPT-5.6 Sol currently leads the published set.
—
AIME 2025
American Invitational Mathematics Examination. Contest math; reasoning-mode models dominate.
—
MMMU
College-level multimodal understanding across diagrams, charts, and exam figures.
—

Modalities

text · tools

753B

Reasoning mode

reasoning

Hybrid and reasoning models spend tokens thinking. That raises GPQA and agents, and also raises latency and bill.

Close on intelligence

  • AClaude Sonnet 555.3
  • OGPT-5.6 Luna52.3
  • GGemini 3.7 Flash56

Same lab

  • GLM-5.3
  • GLM-5.3 Flash

Aperture is a field guide, not a vendor. Scores compiled 28 Aug 2026.

MethodologyHow to pick