Net Good IndexSubmit a correction

OpenAI · OpenAI reasoning models

OpenAI Internal Research Model — 2025-07

Internal / unreleased

Benefit

0.00

Harm

0.00

Net Good

0.00

Verified benefit

0.00

History

Cumulative score

  • Benefit
  • Harm
  • Net
00.200.400.600.801Jul 25Oct 25Jan 26Apr 26Jul 26Oct 26

Domains

Mathematics0.00

Release

Status internal. First dated 19 Jul 2025.

Event timeline

Capability19 Jul 2025

An OpenAI reasoning model reaches IMO 2025 gold-medal standard

In July 2025 OpenAI reported that an experimental reasoning model scored 35/42 on the IMO 2025 paper under contest-like constraints, graded by former medalists.

MathematicsverifiedTier 3 Major1.49