MedXpertQA MM Extended

Opus 5.5
Opus 5.5Max
71.2%
GPT-6 Sol
GPT-6 SolMax
68.0%
Fable 5.1
Fable 5.1High
66.0%
GPT-6.1 Sol
GPT-6.1 SolMax
64.7%
GPT-5.6 Sol
GPT-5.6 SolMax • Pro
64.7%
Opus 5
Opus 5Max
64.1%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
62.7%
GPT-5.4
GPT-5.4xHigh
62.1%
GPT-6 Astra
GPT-6 AstraMax
60.8%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
60.8%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
60.8%
GPT-5.5
GPT-5.5xHigh
60.8%
Muse Spark 1.3
Muse Spark 1.3Max
60.1%
Muse Spark 1.1
Muse Spark 1.1xHigh
58.2%
Muse Spark 1.2
Muse Spark 1.2xHigh
58.2%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
57.5%
Fable 5
Fable 5Max
56.9%
GPT-5.6 Luna
GPT-5.6 LunaMax
56.2%
Sonnet 5.5
Sonnet 5.5Max
55.6%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
54.2%
GLM-5.3-Flash
GLM-5.3-FlashMax
52.9%
Grok 4.7
Grok 4.7xHigh
52.0%
Qwen3.8-Max
Qwen3.8-MaxxHigh
51.6%
Opus 4.8
Opus 4.8Max
51.6%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
51.6%
GPT-5.6 Terra
GPT-5.6 TerraMax
51.0%
Opus 4.7
Opus 4.7Max
51.0%
Inkling
InklingHigh
51.0%
Grok 4.6
Grok 4.6xHigh
48.4%
Haiku 5.5
Haiku 5.5Max
48.4%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
48.4%
Kimi K3
Kimi K3Max
47.7%
Gemini 3.5 Flash Lite
Gemini 3.5 Flash LiteHigh
47.7%
GPT-6 Luna
GPT-6 LunaMax
46.4%
Qwen3.5
Qwen3.5
45.1%
Sonnet 5
Sonnet 5Max
43.8%
Grok 4.5
Grok 4.5High
41.2%
Sonnet 4.6
Sonnet 4.6High
41.2%
MiniMax-M3
MiniMax-M3High
34.6%
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.