OpenWorldEngineer: Science

Chemistry (reaction kinetics from lab records, quantum-chemistry integral kernels) and earth science (earthquake relocation, atmospheric dispersion, storm surge, satellite gap filling)
Fable 5.2
Fable 5.2Max
40.2%
GPT-6 Astra
GPT-6 AstraMax
39.4%
Opus 5.5
Opus 5.5Max
30.4%
GPT-6.1 Sol
GPT-6.1 SolMax
29.6%
Sonnet 5.5
Sonnet 5.5Max
28.2%
Gemini 4 Carbon
Gemini 4 CarbonHigh
25.2%
Gemini 4 Argon
Gemini 4 ArgonHigh
22.8%
Fable 5.1
Fable 5.1Max
19.7%
Kimi K3.1 Pro
Kimi K3.1 ProMax
9.7%
Grok 4.7
Grok 4.7xHigh
8.3%
GLM-5.3
GLM-5.3Max
8.2%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
6.7%
Beam
BeamMax
3.7%
Inkling
InklingMax
1.2%
0%
10%
20%
30%
40%
50%
60%
70%

APEX NEWSLETTER

The latest on frontier AI performance, straight to your inbox.

New benchmarks, leaderboard shifts, and research from the APEX team.

By subscribing, you agree to receive updates from Mercor.
Unsubscribe anytime.