Tihu · Pelican Bench

MiniMax-M3

MiniMax · Model release:

AI reference score 6.74 ± 1.47 · default (best) Last 3 weekly runs · 9 images
Tier comparison
TierSamplesAI reference scoreValid SVG rateMean timeSamples
default · This model version has no selectable reasoning tiers
MiniMax-M3 · default · 2026-10-25 · #2 · 8.38
 6.74 ± 1.47Last 3 weekly runs · 9 images 100%63 s3
MiniMax-M3 · default · 2026-10-25 · #2 · 8.38
default · This model version has no selectable reasoning tiers 6.74 ± 1.47Last 3 weekly runs · 9 images
Valid SVG rate 100% · Mean time 63 s

Latest samples

default · This model version has no selectable reasoning tiers

AI reference score 6.74 ± 1.47 Last 3 weekly runs · 9 images 1 weekly test left
Top tiers of one modelView tier page

SunLatest

MiniMax-M3 · default · 2026-10-25 · #2 · 8.38MiniMax-M3 · default · 2026-10-25 · #3 · 8.23MiniMax-M3 · default · 2026-10-25 · #1 · 7.36

Score trend

default · This model version has no selectable reasoning tiers Normal

2026-10-11 · 6.372026-10-18 · 5.862026-10-19 · 5.862026-10-20 · 5.862026-10-21 · 5.862026-10-23 · 5.862026-10-24 · 5.862026-10-25 · 7.992026-10-26 · 7.99

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

Versions by score

  1. MiniMax-M3
    MiniMax-M3 · default
    default · This model version has no selectable reasoning tiers 6.74Last 3 weekly runs · 9 images

Scores by criterion

Scores by tier
Scoring criteria default · This model version has no selectable reasoning tiers
Pelican likeness8.39
Bicycle correctness7.83
Riding pose7.56
Composition8.78
Obvious errors (higher is better)7.39

Release notes

Original (Chinese)当天 MiniMax-M3 在 MiniMax API 可用。

· View release source ↗