MMMU-Pro Extended

GPT-6.1 Sol
GPT-6.1 SolMax
61.3%
GPT-6 Astra
GPT-6 AstraMax
60.0%
GPT-6 Sol
GPT-6 SolMax
51.9%
Opus 5.5
Opus 5.5Max
51.0%
Fable 5.1
Fable 5.1Max
47.6%
GPT-5.6 Terra
GPT-5.6 TerraMax
47.4%
Sonnet 5.5
Sonnet 5.5Max
44.4%
GPT-5.5
GPT-5.5xHigh
43.8%
GPT-5.4
GPT-5.4xHigh
39.8%
GPT-5.6 Luna
GPT-5.6 LunaMax
39.2%
Fable 5
Fable 5Max
37.6%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
36.4%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
36.4%
Kimi K3
Kimi K3Max
36.0%
Muse Spark 1.1
Muse Spark 1.1xHigh
35.5%
Qwen3.8-Max
Qwen3.8-MaxxHigh
34.8%
GPT-6 Luna
GPT-6 LunaMax
34.8%
Muse Spark 1.3
Muse Spark 1.3xHigh
33.8%
Haiku 5.5
Haiku 5.5Max
31.9%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
31.0%
Muse Spark 1.2
Muse Spark 1.2xHigh
30.2%
Grok 4.5
Grok 4.5High
29.8%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
29.0%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
28.8%
Opus 4.7
Opus 4.7High
28.3%
Grok 4.6
Grok 4.6xHigh
26.0%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
25.0%
Inkling
InklingHigh
24.0%
GLM-5.3-Flash
GLM-5.3-FlashMax
22.6%
Sonnet 4.6
Sonnet 4.6High
19.9%
MiniMax-M3
MiniMax-M3High
18.1%
10%
20%
30%
40%
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.