MMMU-Pro

GPT-6 Astra
GPT-6 AstraMax
87.5%
Opus 5.5
Opus 5.5Max
87.4%
Fable 5.1
Fable 5.1Max
86.1%
Sonnet 5.5
Sonnet 5.5Max
85.8%
GPT-6.1 Sol
GPT-6.1 SolMax
85.8%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
85.3%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
85.2%
Muse Wonder 1.0
Muse Wonder 1.0Max
84.9%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
84.7%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
84.3%
Opus 5
Opus 5Max
84.2%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
83.7%
GPT-5.6 Sol
GPT-5.6 SolMax
83.6%
GPT-6 Sol
GPT-6 SolMax
83.0%
Qwen3.8-Max
Qwen3.8-MaxxHigh
82.8%
GPT-5.5
GPT-5.5xHigh
81.8%
Muse Spark 1.3
Muse Spark 1.3xHigh
81.8%
Muse Spark 1.2
Muse Spark 1.2xHigh
81.4%
Muse Spark 1.1
Muse Spark 1.1xHigh
81.3%
Muse Spark Open
Muse Spark OpenxHigh
81.0%
GPT-5.6 Terra
GPT-5.6 TerraMax
80.9%
GPT-5.4
GPT-5.4xHigh
80.8%
Kimi K3
Kimi K3Max
80.7%
Grok 4.6
Grok 4.6xHigh
80.5%
Opus 4.8
Opus 4.8Max
79.5%
GPT-5.6 Luna
GPT-5.6 LunaMax
79.1%
Haiku 5.5
Haiku 5.5Max
79.1%
Grok 4.5
Grok 4.5High
79.0%
MiniMax-M3
MiniMax-M3High
78.9%
Opus 4.7
Opus 4.7High
78.6%
GLM-5.3-Flash
GLM-5.3-FlashMax
78.4%
GPT-6 Luna
GPT-6 LunaMax
76.6%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
76.6%
Sonnet 5
Sonnet 5Max
75.5%
Sonnet 4.6
Sonnet 4.6High
74.6%
Fable 5
Fable 5Max
72.7%
Inkling
InklingHigh
69.7%
GLM-5.3
GLM-5.3Max
63.1%
50%
60%
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.