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

BenchmarkScoreMetricPercentile
AA GDP.pdf - Real Estate - Criterion Pass Rate81.5Criterion Pass Rate (%)100
FrontierCS 2 - In-place Integer Redistribution51.31Task score (0–100)100
AA-Omniscience Index - Software Engineering (SWE) - Kotlin74.29Omniscience Index98.9
AA CritPt31.71Accuracy (%)98.7
AA Terminal-Bench Science 0.1 - Earth Sciences66.67Pass@1 (%)98.6
AA GDP.pdf31.8All Criteria Pass Rate (%)98.5
DeepsecBench39.49Recall-weighted F2 score (%)98.2
AA GDP.pdf - Construction - Criterion Pass Rate82.36Criterion Pass Rate (%)98.1
ARC-AGI-198.5Accuracy (%)98.1
DuelLab GameBench 2 - Reasoning Variants91.8GameBench2 normalized score (0–100)97.4
Epoch AI - Critpt31.71Score97.4
OpenAI COBOL Migration97.9All-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.