Tihu · Pelican Bench

Qwen3.8-Flash

Alibaba · Model release:

AI reference score 8.39 ± 0.57 Last 2 weekly runs · 6 images 2 weekly tests leftUpdated every Sunday · 2026-10-25Top tiers of one model

Latest samples

SunLatest

Qwen3.8-Flash · default · 2026-10-25 · #1 · 8.67Qwen3.8-Flash · default · 2026-10-25 · #2 · 8.49Qwen3.8-Flash · default · 2026-10-25 · #3 · 7.25

Score trend

default · This model version has no selectable reasoning tiers Normal

2026-10-18 · 8.642026-10-23 · 8.642026-10-24 · 8.642026-10-25 · 8.142026-10-26 · 8.14

5 records in the last 30 days

2026-10-26 · Normal2026-10-25 · Collecting earlier results2026-10-24 · Normal2026-10-23 · Normal2026-10-18 · Collecting earlier results

Earlier samples

default · This model version has no selectable reasoning tiers

Sun

Qwen3.8-Flash · default · 2026-10-18 · #2 · 8.75Qwen3.8-Flash · default · 2026-10-18 · #1 · 8.74Qwen3.8-Flash · default · 2026-10-18 · #3 · 8.42

Versions by score

  1. Qwen3.8-Flash
    Qwen3.8-Flash · default
    default · This model version has no selectable reasoning tiers 8.39Last 2 weekly runs · 6 images

Scores by criterion

Pelican likeness
7.89
Bicycle correctness
8.33
Riding pose
8.28
Composition
8.72
Obvious errors (higher is better)
7.44

Release notes

Original (Chinese)当天在阿里云 Model Studio API 可用，同日开放 Qwen3.8-Flash-Next 权重：https://qwen.ai/blog?id=qwen3.8-flash-next 。

· View release source ↗