GPT-6 Sol (Max): benchmark results

Provider: OpenAI. Access: API.

Unified ELO 1771 ± 1, rank #17 of 3363 rated models, from 90 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MLCR-AA - Conciseness100Conciseness (%)99.4
AutomationBench-AA - Sales - Raw Objective Completion88.68Raw Objective Completion (%)98.9
MLCR-AA - Accuracy96.67Accuracy (%)98.9
AA CritPt30.86Accuracy (%)98.8
AA-Omniscience Index - Software Engineering (SWE) - Rust84Omniscience Index98.6
AA-Omniscience Index - Software Engineering (SWE) - HTML84Omniscience Index98.1
VoxelBench2440Rating98
AA-Omniscience Index - Software Engineering (SWE) - TypeScript88.89Omniscience Index97.9
Artificial Analysis Intelligence Index47.53Intelligence Index97.4
AA Long Context Reasoning83.67Accuracy (%)97.3
AA Humanity's Last Exam47.91Accuracy (%)96.2
AutomationBench-AA - HR - Raw Objective Completion75.71Raw Objective Completion (%)95.7

Interactive version: theaggregate.ai/model?slug=gpt-6-sol-max · How It Works · Data refreshed daily, snapshot 2026-09-23.