GDPval

Opus 5.5
Opus 5.5Max
88.3%
Muse Wonder 1.0
Muse Wonder 1.0Max
87.0%
GPT-6 Astra
GPT-6 AstraMax
86.7%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
86.7%
Fable 5.1
Fable 5.1Max
86.6%
Sonnet 5.5
Sonnet 5.5Max
86.5%
Grok 4.6
Grok 4.6xHigh
86.0%
Gemini 4 Argon
Gemini 4 ArgonHigh
85.9%
Opus 5
Opus 5Max
85.6%
Haiku 5.5
Haiku 5.5Max
85.5%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
85.2%
GPT-5.5
GPT-5.5xHigh
84.6%
Opus 4.8
Opus 4.8Max
84.5%
Kimi K3
Kimi K3Max
84.2%
Sonnet 5
Sonnet 5Max
84.1%
Fable 5
Fable 5Max
83.8%
Muse Spark 1.2
Muse Spark 1.2xHigh
83.8%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
83.8%
GPT-6 Sol
GPT-6 SolMax
83.5%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
83.5%
Qwen3.8-Max
Qwen3.8-MaxxHigh
83.3%
GLM-5.2
GLM-5.2Max
82.9%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
82.6%
Opus 4.7
Opus 4.7Max
82.6%
Sonnet 4.6
Sonnet 4.6High
82.5%
Muse Spark 1.1
Muse Spark 1.1xHigh
82.4%
Grok 4.5
Grok 4.5High
81.7%
GPT-5.6 Terra
GPT-5.6 TerraMax
80.7%
GPT-5.6 Sol
GPT-5.6 SolMax • Pro
80.1%
Beam
BeamMax
80.1%
GPT-6 Luna
GPT-6 LunaMax
80.1%
MiniMax-M3
MiniMax-M3High
79.0%
GPT-5.6 Luna
GPT-5.6 LunaMax
78.9%
DeepSeek-V4-Pro
DeepSeek-V4-ProMax
78.0%
MiniMax-M2.7
MiniMax-M2.7High
76.2%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
75.9%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
75.3%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
74.4%
Inkling
InklingHigh
73.7%
GPT-5.4
GPT-5.4xHigh
73.0%
DeepSeek-V3.2
DeepSeek-V3.2
71.9%
Qwen3.5
Qwen3.5
71.0%
Gemma 4 31B
Gemma 4 31B
68.9%
Kimi K2
Kimi K2High • Thinking
66.2%
Nemotron 3 Ultra
Nemotron 3 UltraHigh
63.5%
GPT-OSS-120B
GPT-OSS-120BHigh
58.9%
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.