MedXpertQA MM

GPT-6 Astra
GPT-6 AstraMax
86.8%
Opus 5.5
Opus 5.5Max
85.7%
GPT-6.1 Sol
GPT-6.1 SolMax
85.7%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
84.7%
Fable 5.1
Fable 5.1Max
83.7%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
83.5%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
83.5%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
82.8%
GPT-6 Sol
GPT-6 SolMax
81.3%
Sonnet 5.5
Sonnet 5.5Max
80.7%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
80.2%
Opus 5
Opus 5Max
79.8%
GPT-5.6 Sol
GPT-5.6 SolMax • Pro
79.5%
Qwen3.8-Max
Qwen3.8-MaxxHigh
78.3%
Muse Spark 1.1
Muse Spark 1.1xHigh
77.0%
GPT-5.5
GPT-5.5xHigh
76.7%
Muse Spark 1.3
Muse Spark 1.3Max
76.3%
Fable 5
Fable 5Max
76.2%
GPT-5.6 Terra
GPT-5.6 TerraMax
75.7%
Muse Spark 1.2
Muse Spark 1.2xHigh
75.7%
Grok 4.6
Grok 4.6xHigh
75.2%
GPT-5.4
GPT-5.4xHigh
74.2%
GLM-5.3-Flash
GLM-5.3-FlashMax
73.7%
Kimi K3
Kimi K3Max
73.2%
Opus 4.7
Opus 4.7Max
72.8%
Opus 4.8
Opus 4.8Max
72.5%
GPT-5.6 Luna
GPT-5.6 LunaMax
70.2%
Grok 4.5
Grok 4.5High
69.5%
Grok 4.7
Grok 4.7xHigh
69.0%
Haiku 5.5
Haiku 5.5Max
67.8%
Gemini 3.5 Flash Lite
Gemini 3.5 Flash LiteHigh
66.7%
Qwen3.5
Qwen3.5
65.8%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
65.7%
GPT-6 Luna
GPT-6 LunaMax
64.8%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
63.5%
Sonnet 5
Sonnet 5Max
63.0%
Sonnet 4.6
Sonnet 4.6High
61.7%
Inkling
InklingHigh
60.0%
MiniMax-M3
MiniMax-M3High
59.7%
GLM-5.3
GLM-5.3Max
49.2%
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.