Tihu · Pelican Bench

GLM 5.3

Zhipu · Model release:

AI reference score 8.34 ± 0.57 Last 3 weekly runs · 9 images 1 weekly test leftUpdated every Sunday · 2026-10-25Top tiers of one model Compare with previous version

Latest samples

SunLatest

GLM 5.3 · default · 2026-10-25 · #3 · 8.83GLM 5.3 · default · 2026-10-25 · #1 · 8.43GLM 5.3 · default · 2026-10-25 · #2 · 7.98

Score trend

default · This model version has no selectable reasoning tiers Normal

2026-10-11 · 8.112026-10-18 · 8.502026-10-19 · 8.502026-10-20 · 8.502026-10-21 · 8.502026-10-23 · 8.502026-10-24 · 8.502026-10-25 · 8.412026-10-26 · 8.41

9 records in the last 30 days

2026-10-26 · Normal2026-10-25 · Collecting earlier results2026-10-24 · Normal2026-10-23 · Normal2026-10-21 · Normal2026-10-20 · Normal2026-10-19 · Normal2026-10-18 · Collecting earlier results2026-10-11 · Collecting earlier results

Earlier samples

default · This model version has no selectable reasoning tiers

Sun

GLM 5.3 · default · 2026-10-18 · #2 · 8.83GLM 5.3 · default · 2026-10-18 · #3 · 8.41GLM 5.3 · default · 2026-10-18 · #1 · 8.27

Sun

GLM 5.3 · default · 2026-10-11 · #1 · 8.78GLM 5.3 · default · 2026-10-11 · #2 · 8.51GLM 5.3 · default · 2026-10-11 · #3 · 7.02

Versions by score

  1. GLM 5.3
    GLM 5.3 · default
    default · This model version has no selectable reasoning tiers 8.34Last 3 weekly runs · 9 images
  2. GLM 5.2
    GLM 5.2 · high
    high 5.14Last 4 weekly runs · 12 images Default tier for this version

Scores by criterion

Pelican likeness
8.67
Bicycle correctness
8.56
Riding pose
8.17
Composition
8.67
Obvious errors (higher is better)
7.83

Release notes

Original (Chinese)当天 GLM 5.3 可用。

· View release source ↗