Long Context Reasoning (AA-LCR v1.1)

Fable 5.1
Fable 5.1Max
87.5%
Fable 5
Fable 5Max
85.5%
GPT-5.6 Sol
GPT-5.6 SolMax • Pro
85.3%
Opus 5.5
Opus 5.5Max
85.0%
Kimi K3
Kimi K3Max
84.3%
GPT-5.5
GPT-5.5xHigh
83.8%
GPT-6 Sol
GPT-6 SolMax
83.5%
Sonnet 5.5
Sonnet 5.5Max
83.5%
GPT-5.6 Terra
GPT-5.6 TerraMax
83.3%
MiniMax-M3
MiniMax-M3High
83.3%
Opus 4.7
Opus 4.7Max
83.0%
Muse Wonder 1.0
Muse Wonder 1.0Max
83.0%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
82.8%
GPT-6 Luna
GPT-6 LunaMax
82.3%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
82.3%
Muse Spark 1.3
Muse Spark 1.3Max
82.3%
Qwen 3.8 27B
Qwen 3.8 27BxHigh
82.3%
Haiku 5.5
Haiku 5.5Max
82.3%
Opus 5
Opus 5Max
82.0%
Sonnet 5
Sonnet 5Max
81.8%
GPT-5.4
GPT-5.4xHigh
81.5%
GPT-5.6 Luna
GPT-5.6 LunaMax
81.2%
GPT-6.1 Sol
GPT-6.1 SolMax
81.2%
Qwen3.8-Max
Qwen3.8-MaxxHigh
80.7%
Sonnet 4.6
Sonnet 4.6High
80.5%
GPT-6 Astra
GPT-6 AstraMax
80.5%
Muse Spark Open
Muse Spark OpenxHigh
80.5%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
80.2%
GLM-5.3-Flash
GLM-5.3-FlashMax
79.7%
Opus 4.8
Opus 4.8Max
79.5%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
79.2%
Muse Spark 1.2
Muse Spark 1.2xHigh
79.0%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
78.7%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
78.7%
GLM-5.2
GLM-5.2Max
78.7%
DeepSeek-V4-Pro-0813
DeepSeek-V4-Pro-0813Max
78.5%
Muse Spark 1.1
Muse Spark 1.1xHigh
78.2%
Grok 4.6
Grok 4.6xHigh
78.2%
GLM-5.3
GLM-5.3Max
78.0%
Beam
BeamMax
78.0%
Grok 4.5
Grok 4.5High
77.5%
MiniMax-M2.7
MiniMax-M2.7High
77.5%
Grok 4.7
Grok 4.7xHigh
77.4%
Opus 4.6
Opus 4.6Max
77.2%
Gemini 3.5 Flash Lite
Gemini 3.5 Flash LiteHigh
76.7%
DeepSeek-V4-Pro
DeepSeek-V4-ProMax
76.2%
Qwen3.5
Qwen3.5
76.0%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
74.8%
Inkling
InklingHigh
74.5%
Nemotron 3 Ultra
Nemotron 3 UltraHigh
73.5%
Kimi K2
Kimi K2High • Thinking
73.3%
Gemma 4 31B
Gemma 4 31B
73.3%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
73.0%
DeepSeek-V3.2
DeepSeek-V3.2
69.5%
GPT-OSS-120B
GPT-OSS-120BHigh
54.2%
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.