GPT-6.1 Sol (Low): benchmark results
Provider: OpenAI. Released 2026-09-29. Access: API.
Aggregate Rating 1882 ± 10, rank #59 of 2245 rated models, from 163 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CMDB-1500 (Text) | 80 | Accuracy (%), fixed denominator of 1,200 questions (invalid | 100 |
| EnigmaForge | 84.5 | Task success (%) over 600 procedurally generated story insta | 100 |
| EnigmaForge - Fact F1 | 98.5 | World-fact recovery F1 (%) over 600 instances, all items | 100 |
| EnigmaForge - Intuition | 83.8 | Task success (%) on implicit-condition instances, where the | 100 |
| AA Long Context Reasoning | 84 | Accuracy (%) | 97.7 |
| AA Omniscience | 37.63 | Score | 96 |
| AA-Omniscience Index - Software Engineering (SWE) - PHP | 82.35 | Omniscience Index | 95.4 |
| AA-Omniscience Accuracy | 58.87 | Accuracy (%) | 95.1 |
| ParseBench - Tables | 92.46 | GTRM Score (GriTS + TableRecordMatch) | 95 |
| SelfBench - vercel/eve | 73.68 | Task success (%) on 38 tasks rebuilt from the repository's m | 94.4 |
| AA GDP.pdf - Construction - Criterion Pass Rate | 77.63 | Criterion Pass Rate (%) | 94.2 |
| RuneBench | 6.75 | Mean ln(1 + peak XP/min) across sixteen 30-minute skills; hi | 94.1 |
Interactive version: theaggregate.ai/model?slug=gpt-6-1-sol-low · How It Works · Data refreshed daily, snapshot 2026-11-16.