AIME 2025

Opus 5
Opus 5Max
100.0%
Fable 5
Fable 5Max
100.0%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
100.0%
GPT-5.5
GPT-5.5xHigh
100.0%
GPT-5.6 Sol
GPT-5.6 SolMaxPro
100.0%
GPT-5.6 Terra
GPT-5.6 TerraMax
100.0%
Muse Spark 1.1
Muse Spark 1.1xHigh
100.0%
GPT-6 Astra
GPT-6 AstraxHigh
100.0%
Fable 5.1
Fable 5.1High
100.0%
GPT-5.6 Luna
GPT-5.6 LunaMax
99.2%
GPT-5.4
GPT-5.4xHigh
99.2%
Opus 4.8
Opus 4.8Max
98.3%
Grok 4.5
Grok 4.5High
98.3%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
98.3%
DeepSeek-V4-Pro
DeepSeek-V4-ProMax
98.1%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
96.9%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
96.7%
Kimi K2
Kimi K2HighThinking
96.7%
GLM-5.2
GLM-5.2Max
96.7%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
95.8%
Kimi K3
Kimi K3Max
95.8%
GPT-OSS-120B
GPT-OSS-120BHigh
94.2%
Opus 4.7
Opus 4.7Max
93.3%
Nemotron 3 Ultra
Nemotron 3 UltraHigh
93.3%
Inkling
InklingHigh
93.3%
DeepSeek-V3.2
DeepSeek-V3.2
93.3%
MiniMax-M3
MiniMax-M3High
91.7%
Sonnet 4.6
Sonnet 4.6High
90.0%
MiniMax-M2.7
MiniMax-M2.7High
88.3%
Sonnet 5
Sonnet 5Max
88.3%
Gemma 4 31B
Gemma 4 31B
84.2%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
81.7%
70%
80%
90%
100%

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.