GPQA Diamond

GPT-6 Astra
GPT-6 AstraxHigh
96.2%
Sonnet 5.5
Sonnet 5.5Max
95.2%
GPT-6.1 Sol
GPT-6.1 SolMax
95.1%
GPT-5.6 Sol
GPT-5.6 SolMax • Pro
94.9%
GPT-5.5
GPT-5.5xHigh
94.6%
GPT-6 Sol
GPT-6 SolMax
94.4%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
94.2%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
94.2%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
93.9%
Grok 4.6
Grok 4.6xHigh
93.8%
Opus 5
Opus 5Max
93.6%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
93.4%
GPT-5.6 Terra
GPT-5.6 TerraMax
93.2%
GPT-5.4
GPT-5.4xHigh
93.2%
DeepSeek-V4-Pro-0813
DeepSeek-V4-Pro-0813Max
93.2%
Kimi K3
Kimi K3Max
92.7%
Qwen3.8-Max
Qwen3.8-MaxxHigh
92.5%
Grok 4.5
Grok 4.5High
92.4%
Opus 4.8
Opus 4.8Max
92.0%
GPT-5.6 Luna
GPT-5.6 LunaMax
91.8%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
91.4%
Fable 5.1
Fable 5.1Max
91.4%
Opus 5.5
Opus 5.5Max
91.3%
Muse Spark 1.3
Muse Spark 1.3Max
91.3%
GLM-5.3
GLM-5.3Max
91.3%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
91.2%
Muse Spark 1.1
Muse Spark 1.1xHigh
90.8%
Beam
BeamMax
90.7%
MiniMax-M3
MiniMax-M3High
90.5%
GLM-5.2
GLM-5.2Max
90.2%
GPT-6 Luna
GPT-6 LunaMax
89.9%
Haiku 5.5
Haiku 5.5Max
89.8%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
89.5%
DeepSeek-V4-Pro
DeepSeek-V4-ProMax
89.4%
Muse Spark Open
Muse Spark OpenxHigh
88.4%
Nemotron 3 Ultra
Nemotron 3 UltraHigh
87.8%
Inkling
InklingHigh
87.2%
Opus 4.7
Opus 4.7Max
86.4%
MiniMax-M2.7
MiniMax-M2.7High
86.0%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
85.7%
Gemma 4 31B
Gemma 4 31B
85.5%
Muse Spark 1.2
Muse Spark 1.2xHigh
85.3%
DeepSeek-V3.2
DeepSeek-V3.2
85.2%
Fable 5
Fable 5Max
85.0%
Sonnet 4.6
Sonnet 4.6High
84.7%
Kimi K2
Kimi K2High • Thinking
83.7%
Sonnet 5
Sonnet 5Max
80.6%
GPT-OSS-120B
GPT-OSS-120BHigh
77.5%
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.