APEX-Agents: Corporate Lawyer

Created by experts from Latham & Watkins, Skadden, Cravath
Gemini 4 Argon
Gemini 4 ArgonHigh
76.7%
Gemini 4 Carbon
Gemini 4 CarbonHigh
73.8%
GPT-6 Astra
GPT-6 AstraMax
73.4%
Fable 5.1
Fable 5.1Max
71.9%
Opus 5.5
Opus 5.5Max
71.2%
Opus 5
Opus 5Max
70.0%
Sonnet 5.5
Sonnet 5.5Max
69.6%
Kimi K3.1 Pro
Kimi K3.1 ProMax
68.6%
Fable 5
Fable 5Max
67.8%
Muse Wonder 1.0
Muse Wonder 1.0Max
67.2%
GLM-5.3-Flash
GLM-5.3-FlashMax
66.9%
Muse Spark 1.3
Muse Spark 1.3xHigh
66.6%
DeepSeek-V4.1-Flash-1017
DeepSeek-V4.1-Flash-1017Max
66.6%
Qwen3.8-Max
Qwen3.8-MaxxHigh
66.1%
GLM-5.3
GLM-5.3Max
65.9%
MiniMax-M3.1-Flash
MiniMax-M3.1-FlashMax
65.9%
Mistral Large 4
Mistral Large 4High
64.5%
GPT-6.1 Sol
GPT-6.1 SolMax
63.4%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
63.3%
GPT-5.6 Terra
GPT-5.6 TerraMax
63.1%
Grok 4.6
Grok 4.6xHigh
62.8%
Opus 4.8
Opus 4.8Max
62.8%
MiMo V2.6 Flash RL
MiMo V2.6 Flash RLAuto
62.5%
GPT-5.6 Sol
GPT-5.6 SolMax • Pro
61.9%
Sonnet 5
Sonnet 5Max
61.6%
Muse Spark 1.2
Muse Spark 1.2xHigh
61.6%
DeepSeek-V4-Pro-0813
DeepSeek-V4-Pro-0813Max
60.7%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
60.4%
Opus 4.7
Opus 4.7Max
60.3%
Mercury 3
Mercury 3High
60.1%
Kimi K3
Kimi K3Max
60.0%
Haiku 5.5
Haiku 5.5Max
60.0%
Muse Spark Open
Muse Spark OpenxHigh
59.8%
GPT-5.5
GPT-5.5xHigh
59.7%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
59.7%
GLM-5.2
GLM-5.2Max
59.4%
MiMo V2.6 Pro
MiMo V2.6 ProAuto
59.1%
Qwen 3.8 27B
Qwen 3.8 27BxHigh
58.8%
GPT-5.6 Luna
GPT-5.6 LunaMax
58.4%
Grok 4.5
Grok 4.5High
58.1%
GPT-6.1 Terra
GPT-6.1 TerraMax
57.7%
GPT-5.4
GPT-5.4xHigh
57.5%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
57.3%
Muse Spark 1.1
Muse Spark 1.1xHigh
56.9%
GPT-6 Sol
GPT-6 SolMax
56.2%
Opus 4.6
Opus 4.6Max
55.9%
GPT-6 Luna
GPT-6 LunaMax
55.6%
Sonnet 4.6
Sonnet 4.6High
55.3%
Beam
BeamMax
55.1%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
54.2%
GLM-5.1
GLM-5.1
53.7%
Grok 4.7
Grok 4.7xHigh
52.8%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
50.9%
Inkling
InklingHigh
49.7%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
49.7%
MiniMax-M3
MiniMax-M3High
47.6%
Nemotron 3.5 Super VL
Nemotron 3.5 Super VLHigh
44.1%
Gemini 3.5 Flash Lite
Gemini 3.5 Flash LiteHigh
43.4%
Nemotron 3 Ultra
Nemotron 3 UltraHigh
41.9%
DeepSeek-V3.2
DeepSeek-V3.2
41.8%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
39.1%
Nemotron 3.5 Bolt
Nemotron 3.5 BoltHigh
38.1%
Qwen3.5
Qwen3.5
35.6%
GPT-OSS-120B
GPT-OSS-120BHigh
12.2%
0%
10%
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.