Tihu · Pelican Bench

Qwen3.8-Max

Alibaba · Model release:

AI reference score 8.60 ± 0.39 Last 3 weekly runs · 9 images 1 weekly test leftUpdated every Sunday · 2026-10-25Top tiers of one model

Latest samples

SunLatest

Qwen3.8-Max · default · 2026-10-25 · #2 · 8.52Qwen3.8-Max · default · 2026-10-25 · #3 · 8.17Qwen3.8-Max · default · 2026-10-25 · #1 · 7.80

Score trend

default · This model version has no selectable reasoning tiers Normal

2026-10-11 · 8.892026-10-18 · 8.742026-10-19 · 8.742026-10-20 · 8.742026-10-21 · 8.742026-10-23 · 8.742026-10-24 · 8.742026-10-25 · 8.162026-10-26 · 8.16

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

Qwen3.8-Max · default · 2026-10-18 · #3 · 8.89Qwen3.8-Max · default · 2026-10-18 · #2 · 8.71Qwen3.8-Max · default · 2026-10-18 · #5 · 8.63Invalid SVGInvalid SVG

Sun

Qwen3.8-Max · default · 2026-10-11 · #1 · 8.98Qwen3.8-Max · default · 2026-10-11 · #3 · 8.87Qwen3.8-Max · default · 2026-10-11 · #2 · 8.82

Versions by score

  1. Qwen3.8-Max
    Qwen3.8-Max · default
    default · This model version has no selectable reasoning tiers 8.60Last 3 weekly runs · 9 images

Scores by criterion

Pelican likeness
8.44
Bicycle correctness
8.67
Riding pose
7.56
Composition
8.50
Obvious errors (higher is better)
7.33

Release notes

Original (Chinese)当天在阿里云 Model Studio API 与 QwenWork 可用。

· View release source ↗