Harvey LAB

Opus 5
Opus 5Max
17.8%
Kimi K3
Kimi K3Max
14.9%
Fable 5
Fable 5Max
14.4%
Qwen 3.8-Max
Qwen 3.8-MaxxHigh
11.9%
DeepSeek-V4-Pro-0813
DeepSeek-V4-Pro-0813Max
11.4%
Grok 4.5
Grok 4.5High
10.7%
Opus 4.8
Opus 4.8Max
9.4%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
9.3%
Opus 4.7
Opus 4.7Max
8.7%
Sonnet 5
Sonnet 5Max
8.6%
DeepSeek-V4-Pro
DeepSeek-V4-ProMax
4.5%
GPT-5.5
GPT-5.5xHigh
4.1%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
4.1%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
2.7%
GPT-5.6 Sol
GPT-5.6 SolMaxPro
2.7%
MiniMax-M2.7
MiniMax-M2.7High
1.9%
GPT-5.4
GPT-5.4xHigh
1.2%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
0.7%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
0.1%
0%
10%
20%
30%
40%

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.