Tihu · Pelican Bench

GPT-6.1 Terra

OpenAI · Model release:

AI reference score 7.82 ± 0.76 Last 2 weekly runs · 6 images 2 weekly tests leftUpdated every Sunday · 2026-11-01Top tiers of one model Compare with previous version

Latest samples

SunLatest

GPT-6.1 Terra · max · 2026-11-01 · #1 · 7.71GPT-6.1 Terra · max · 2026-11-01 · #2 · 7.53GPT-6.1 Terra · max · 2026-11-01 · #3 · 6.55

Score trend

max Collecting earlier results

2026-10-26 · 8.372026-11-01 · 7.26

2 records in the last 30 days

2026-11-01 · Collecting earlier results2026-10-26 · Collecting earlier results

Earlier samples

max

Mon

GPT-6.1 Terra · max · 2026-10-26 · #2 · 8.70GPT-6.1 Terra · max · 2026-10-26 · #1 · 8.46GPT-6.1 Terra · max · 2026-10-26 · #3 · 7.95

Versions by score

  1. GPT-6.1 Terra
    GPT-6.1 Terra · max
    max 7.82Last 2 weekly runs · 6 images
  2. GPT-5.6 Terra
    GPT-5.6 Terra · max
    max 6.59Last 4 weekly runs · 12 images

Scores by criterion

Pelican likeness
8.00
Bicycle correctness
7.42
Riding pose
5.92
Composition
7.67
Obvious errors (higher is better)
7.17

Release notes

Original (Chinese)当天向 ChatGPT Work（Plus/Pro/Business/Enterprise/Edu）、Codex 及 API（gpt-6.1-terra）开放；公告写明 Chat 暂未上线。

· View release source ↗