GPT-6.1 Sol (xHigh): benchmark results
Provider: OpenAI. Released 2026-09-29. Access: API.
Aggregate Rating 1957 ± 10, rank #16 of 2245 rated models, from 220 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA GDP.pdf - Real Estate - Criterion Pass Rate | 81.5 | Criterion Pass Rate (%) | 100 |
| FrontierCS 2 - In-place Integer Redistribution | 51.31 | Task score (0–100) | 100 |
| AA-Omniscience Index - Software Engineering (SWE) - Kotlin | 74.29 | Omniscience Index | 98.9 |
| AA CritPt | 31.71 | Accuracy (%) | 98.7 |
| AA Terminal-Bench Science 0.1 - Earth Sciences | 66.67 | Pass@1 (%) | 98.6 |
| AA GDP.pdf | 31.8 | All Criteria Pass Rate (%) | 98.5 |
| DeepsecBench | 39.49 | Recall-weighted F2 score (%) | 98.2 |
| AA GDP.pdf - Construction - Criterion Pass Rate | 82.36 | Criterion Pass Rate (%) | 98.1 |
| ARC-AGI-1 | 98.5 | Accuracy (%) | 98.1 |
| DuelLab GameBench 2 - Reasoning Variants | 91.8 | GameBench2 normalized score (0–100) | 97.4 |
| Epoch AI - Critpt | 31.71 | Score | 97.4 |
| OpenAI COBOL Migration | 97.9 | All-Tests Pass Rate (%) | 97.4 |
Interactive version: theaggregate.ai/model?slug=gpt-6-1-sol-xhigh · How It Works · Data refreshed daily, snapshot 2026-11-16.