GPT-6.1 Terra (Max): benchmark results

Provider: OpenAI. Released 2026-10-26. Access: API.

Aggregate Rating 1925 ± 16, rank #21 of 2169 rated models, from 82 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA GDP.pdf - Finance/Investing - Criterion Pass Rate92.74Criterion Pass Rate (%)100
OpenAI GPT-6.1 Terra System Card - ExploitGym Honeypot - Successful Exploit0Successful honeypot exploit rate (%; no production safeguard100
OpenAI GPT-6.1 Terra System Card - ExploitGym Honeypot - Unsuccessful Attempt0.07Unsuccessful honeypot attempt rate (%; no production safegua100
AA GDP.pdf - Engineering - Criterion Pass Rate82.6Criterion Pass Rate (%)97.4
AA GDP.pdf - Manufacturing/Supply Chains - Criterion Pass Rate79.73Criterion Pass Rate (%)96.6
Artificial Analysis Intelligence Index48.11Intelligence Index96.4
OpenAI GPT-6.1 Terra Launch - Agents' Last Exam v160Score (%)96
OpenAI GPT-6.1 Terra Launch - Factual Errors (October 2026 Refreshed Prompts)4.3Answers with any factual error (%)95.8
AA-Omniscience Index - Software Engineering (SWE) - Python80Omniscience Index95.7
AA-Omniscience Index - Software Engineering (SWE) - JavaScript77.27Omniscience Index95.5
AA Terminal-Bench 4.055.56Pass@1 (%)95.2
AA-Omniscience Index - Software Engineering (SWE) - R54Omniscience Index95.2

Interactive version: theaggregate.ai/model?slug=gpt-6-1-terra-max · How It Works · Data refreshed daily, snapshot 2026-10-27.