PhD-level scientific reasoning.
Graduate-level, 'Google-proof' multiple-choice science questions written by domain experts.
Model
Score
GPT-6 AstraxHigh
96.2%
Sonnet 5.5Max
95.2%
GPT-6.1 SolMax
95.1%
GPT-5.6 SolMax • Pro
94.9%
GPT-5.5xHigh
94.6%
APEX NEWSLETTER
New benchmarks, leaderboard shifts, and research from the APEX team.
By subscribing, you agree to receive updates from Mercor.Unsubscribe anytime.