Expert-level chemistry reasoning and problem-solving.
500 expert-prepared advanced chemistry problems. Each is scored on its reasoning path against an expert-written solution, not just on the final answer.
Model
Score
GPT-6 AstraxHigh
80.3%
GPT-6 AstraMax
75.9%
Opus 5.5Max
79.6%
GPT-6.1 SolMax
77.8%
Sonnet 5.5Max
75.4%
GPT-5.6 SolMax • Pro
74.9%
GPT-5.6 SolxHigh
70.9%
APEX NEWSLETTER
New benchmarks, leaderboard shifts, and research from the APEX team.
By subscribing, you agree to receive updates from Mercor.Unsubscribe anytime.