MMLU-Pro

Opus 5.5
Opus 5.5Max
93.4%
Fable 5.1
Fable 5.1Max
93.0%
Opus 5
Opus 5Max
92.0%
GPT-6 Astra
GPT-6 AstraMax
91.5%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
91.3%
Sonnet 5.5
Sonnet 5.5Max
91.0%
GPT-6.1 Sol
GPT-6.1 SolMax
91.0%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
90.7%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
90.6%
Opus 4.8
Opus 4.8Max
90.0%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
90.0%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
90.0%
Opus 4.7
Opus 4.7Max
89.9%
GPT-5.6 Sol
GPT-5.6 SolMax • Pro
89.9%
Muse Spark 1.1
Muse Spark 1.1xHigh
89.9%
Muse Wonder 1.0
Muse Wonder 1.0Max
89.6%
Grok 4.6
Grok 4.6xHigh
89.4%
Kimi K3
Kimi K3Max
89.3%
GPT-5.5
GPT-5.5xHigh
88.9%
GPT-6 Sol
GPT-6 SolMax
88.9%
Qwen3.8-Max
Qwen3.8-MaxxHigh
88.8%
Grok 4.7
Grok 4.7xHigh
88.8%
Sonnet 5
Sonnet 5Max
88.5%
GPT-5.4
GPT-5.4xHigh
88.2%
Grok 4.5
Grok 4.5High
88.2%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
88.2%
GPT-5.6 Terra
GPT-5.6 TerraMax
88.1%
Sonnet 4.6
Sonnet 4.6High
88.0%
Qwen3.5
Qwen3.5
88.0%
GLM-5.3
GLM-5.3Max
88.0%
DeepSeek-V4-Pro-0813
DeepSeek-V4-Pro-0813Max
88.0%
Muse Spark Open
Muse Spark OpenxHigh
87.6%
Haiku 5.5
Haiku 5.5Max
87.4%
GLM-5.3-Flash
GLM-5.3-FlashMax
87.3%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
87.1%
Inkling
InklingHigh
86.8%
DeepSeek-V4-Pro
DeepSeek-V4-ProMax
86.5%
GPT-5.6 Luna
GPT-5.6 LunaMax
86.5%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
86.4%
GPT-6 Luna
GPT-6 LunaMax
86.2%
Nemotron 3 Ultra
Nemotron 3 UltraHigh
86.0%
GLM-5.2
GLM-5.2Max
85.9%
Gemma 4 31B
Gemma 4 31B
85.8%
MiniMax-M3
MiniMax-M3High
84.6%
Kimi K2
Kimi K2High • Thinking
84.3%
Beam
BeamMax
79.8%
MiniMax-M2.7
MiniMax-M2.7High
79.6%
Fable 5
Fable 5Max
79.4%
DeepSeek-V3.2
DeepSeek-V3.2
76.5%
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.