GPT-6.2 Astra1,318 Elo
OpenAI GPT-6.2 launch / blinded human preferenceevaluation: Blinded human preference between interactive 3D experiences from the same prompt
OpenAI ↗Human preference ratings for interactive 3D browser experiences.
| Model / creator | Version | Reported score |
|---|---|---|
| OpenAI GPT-6.2 launch / blinded human preference | 1,318 Elo | |
| OpenAI GPT-6.2 launch / blinded human preference | 1,259 Elo |
evaluation: Blinded human preference between interactive 3D experiences from the same prompt
OpenAI ↗evaluation: Blinded human preference between interactive 3D experiences from the same prompt
OpenAI ↗Web development preference ratings.
τ²-benchTests whether a customer-service agent can resolve requests while using tools and following company policies, helping you assess opportunities to reduce manual support work.
PostTrainBench LiteImproves an already-trained language model through further training within a fixed compute and time budget..