GPT-6.1 Terra (Medium): benchmark results
Provider: OpenAI. Released 2026-10-26. Access: API.
Aggregate Rating 1871 ± 18, rank #56 of 2169 rated models, from 67 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA-Omniscience Index - Software Engineering (SWE) - JavaScript | 79.09 | Omniscience Index | 96.4 |
| AA-Omniscience Index - Software Engineering (SWE) - PHP | 80 | Omniscience Index | 96.1 |
| AA GDP.pdf - Engineering - Criterion Pass Rate | 81.85 | Criterion Pass Rate (%) | 95.7 |
| AA-Omniscience Index - Software Engineering (SWE) - Java | 47 | Omniscience Index | 95.1 |
| AA-Omniscience Index - Software Engineering (SWE) - TypeScript | 82.22 | Omniscience Index | 94.5 |
| AA-Omniscience Index - Software Engineering (SWE) - R | 52 | Omniscience Index | 94.3 |
| AA GDP.pdf | 28.4 | All Criteria Pass Rate (%) | 94 |
| AA-Omniscience Index - Software Engineering (SWE) - Julia | 64 | Omniscience Index | 94 |
| AA-Omniscience Index - Software Engineering (SWE) - Python | 77 | Omniscience Index | 94 |
| AA-Omniscience Index - Software Engineering (SWE) | 69.1 | Omniscience Index | 93.7 |
| Maze-Bench | 79.63 | Mean Score | 93 |
| AA-Omniscience Index - Software Engineering (SWE) - HTML | 72 | Omniscience Index | 92.8 |
Interactive version: theaggregate.ai/model?slug=gpt-6-1-terra-medium · How It Works · Data refreshed daily, snapshot 2026-10-27.