GPT-5.6 Terra (Max) — benchmark results
GPT-5.6 Terra evaluated at the max reasoning-effort setting. Provider: OpenAI. Released 2026-07-09. Access: API.
Unified ELO 2051 ± 39, rank #14 of 1776 rated models, from 51 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Aikido CVE Rediscovery | 83.3 | Recall (%) | 100 |
| AA CritPt | 30 | Accuracy (%) | 99.8 |
| Artificial Analysis Intelligence Index | 54.95 | Intelligence Index | 98.9 |
| AA Long Context Reasoning | 74 | Accuracy (%) | 98.3 |
| AA Humanity's Last Exam | 41.8 | Accuracy (%) | 98.1 |
| AA GPQA Diamond | 92.53 | Accuracy (%) | 97.6 |
| Tau3 Banking | 31.75 | Success Rate (%) | 97.6 |
| ARC-AGI-1 | 96.5 | Accuracy (%) | 97.5 |
| AA Terminal-Bench Hard | 57.58 | Accuracy (%) | 97.3 |
| OTIS Mock AIME 2024-25 | 99.72 | Accuracy (%) | 97.1 |
| AA SciCode | 53.94 | Accuracy (%) | 97 |
| AA Omniscience - Software Engineering (SWE) - Go | 74 | Accuracy (%) | 96.7 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-terra-max · How the rankings work · Data refreshed daily, snapshot 2026-07-22.