Frontier Log

Benchmark · InactiveSuperseded by Agents' Last Exam v1.1

Agents' Last Exam v1

Created by UC Berkeley RDI, 3 Jun 2026 · Higher is better · Website

0204060Jul 202653.6%GPT-5.6 Sol0204060Jul 202653.6%GPT-5.6 Sol

Settings and run setups

Task setScoringProviders
All tasks (152)Pass rateAlibabaMiniMaxZ.ai
CLI subset (105)Pass rateDeepSeekZ.ai
All tasks (152)ScoreOpenAI
CLI subset (105)ScoreOpenAI
Not statedPass rateGoogleAlibaba
Not statedScoreAlibaba
CLI subset (105)Not statedZ.aiTencent
Not statedNot statedOpenAIZ.ai

Download image

Results

ModelScoreSource
GPT-5.6 Sol9 Jul 202653.6%GPT-5.6: Frontier intelligence that scales with your ambitionCorroborated The same number is printed in 2 other lab documents: 1 2harness not stated · effort not stated · headline figure · Setting from UC Berkeley RDI’s leaderboard

All benchmarks