Back to Leaderboard

OpenAI Rank #2

gpt-5.2-chat

Evaluated on January 21, 2026

Overall Score

10.0

33 / 33 tasks ran

Score Breakdown

Easy

20% weight

32.5

20 / 20 tasks ran

Tasks requiring < 1 hour

Medium

35% weight

10.0

10 / 10 tasks ran

Tasks requiring a few hours

Hard

45% weight

0.0

3 / 3 tasks ran

Tasks requiring > 1 day

Tasks ran = tasks succesfully attempted (was not refused by the provider's filters).