New: GPT-6.2 benchmark report is here.Read the report ↗

Best LLMs on AA-3D

AA-3D

Human preference ratings for interactive 3D browser experiences.

Updated: Data as of:
Limited reportingSaturation: not applicable
Official benchmark
AA-3D results. Each row identifies its benchmark version and evaluation track. Scores from different versions are not directly comparable. Best effort from the latest stored report date per model and version.
Model / creatorVersionReported score
GPT-6.2 AstraOpenAI · ProprietaryOpenAI GPT-6.2 launch / blinded human preference1,318 Elo
GPT-6.2 SolOpenAI · ProprietaryOpenAI GPT-6.2 launch / blinded human preference1,259 Elo
View all 2 published reports
GPT-6.2 Astra1,318 Elo
OpenAI GPT-6.2 launch / blinded human preference

evaluation: Blinded human preference between interactive 3D experiences from the same prompt

OpenAI ↗
GPT-6.2 Sol1,259 Elo
OpenAI GPT-6.2 launch / blinded human preference

evaluation: Blinded human preference between interactive 3D experiences from the same prompt

OpenAI ↗