GPT-5.6 Terra (xHigh) — benchmark results
GPT-5.6 Terra evaluated at the xhigh reasoning-effort setting. Provider: OpenAI. Released 2026-07-09. Access: API.
Unified ELO 1979 ± 34, rank #31 of 1776 rated models, from 47 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Terminal-Bench Hard | 62.88 | Accuracy (%) | 99.5 |
| AA CritPt | 27.14 | Accuracy (%) | 98.8 |
| Artificial Analysis Intelligence Index | 51.6 | Intelligence Index | 97.6 |
| AA Humanity's Last Exam | 40.04 | Accuracy (%) | 97 |
| AA Omniscience - Software Engineering (SWE) - Go | 74 | Accuracy (%) | 96.7 |
| AA Omniscience - Software Engineering (SWE) - Python | 78.5 | Accuracy (%) | 96.4 |
| AA Omniscience - Software Engineering (SWE) - Rust | 80 | Accuracy (%) | 96 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 77.27 | Accuracy (%) | 95.5 |
| AA Long Context Reasoning | 71.33 | Accuracy (%) | 95.4 |
| AA GPQA Diamond | 90.81 | Accuracy (%) | 95.1 |
| AA Omniscience - Health | 41.8 | Accuracy (%) | 94.9 |
| AA Omniscience - Software Engineering (SWE) - Java | 55 | Accuracy (%) | 94.9 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-terra-xhigh · How the rankings work · Data refreshed daily, snapshot 2026-07-22.