← leaderboard

GLM 5.2

CALIBRATING

Z.AI · z-ai/glm-5.2 · verdict as of 2026-07-03

Daily test history (90 days, baseline band = trailing mean ± 2σ)

Structured Extraction

CALIBRATING

Code Generation

CALIBRATING

Web Design

CALIBRATING

Instruction Following

CALIBRATING

Math & Reasoning

CALIBRATING

Report Analysis

CALIBRATING

Summarization

CALIBRATING

Customer Service

CALIBRATING

Game Design

CALIBRATING

Creative Writing

CALIBRATING

Serving providers (last 30 days)

striped = multiple providers served this model that day (hover for detail)

Public benchmarks overall 75.4

MMLU-Pro

85

GPQA Diamond

80

SWE-bench Verified

68

LMArena Elo

1420

AIME 2025

82

retrieved 2026-07-02 from public sources — see methodology

Recent samples (latest run, one per test case)