OpenAI GPT-6.1 Terra System Card - ExploitBench (Max Tested Solution Length): leaderboard
ACE-normalized mean capability (%); GPT-6.1 Terra October 26, 2026 system-card cohort; native printed labels, with evaluation and configuration boundaries in board/model names. Metric: ACE-normalized mean capability (%).
Metric: ACE-normalized mean capability (%). Source: deploymentsafety.openai.com. Saturation forecast: Around January 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 100 | #5 |
| 2 | GPT-6.1 Sol | 99.7 | #6 |
| 3 | GPT-6.1 Terra | 97.1 | #10 |
| 4 | GPT-6 Sol | 81.7 | #17 |
| 5 | GPT-5.6 Sol | 78.5 | #20 |
| 6 | GPT-6 Luna | 43.4 | #60 |
No result here: #3 Claude Opus 5.5, #8 Gemini 4 Argon, #9 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-6-1-terra-system-card-exploitbench-max-tested-solution-length · How It Works · Data refreshed daily, snapshot 2026-10-27.