HLE Extended

GPT-5.6 Terra
GPT-5.6 TerraMax
70.7%
Opus 5
Opus 5High
61.0%
Fable 5
Fable 5High
58.7%
GPT-5.6 Luna
GPT-5.6 LunaMax
57.5%
GPT-5.4
GPT-5.4xHigh
56.1%
GPT-6 Luna
GPT-6 LunaMax
53.3%
Opus 4.8
Opus 4.8High
49.4%
Qwen3.8-Max
Qwen3.8-MaxxHigh
47.1%
Grok 4.6
Grok 4.6xHigh
45.8%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
45.3%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
36.8%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
36.1%
Kimi K3
Kimi K3Max
35.0%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
31.6%
Opus 4.7
Opus 4.7High
31.2%
Sonnet 5
Sonnet 5High
29.1%
GLM-5.2
GLM-5.2Max
25.8%
Grok 4.5
Grok 4.5High
25.4%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
19.6%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
14.8%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
13.7%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
13.3%
Sonnet 4.6
Sonnet 4.6High
10.9%
DeepSeek-V3.2
DeepSeek-V3.2
8.1%
GPT-OSS-120B
GPT-OSS-120BHigh
8.1%
MiniMax-M2.7
MiniMax-M2.7High
6.6%
MiniMax-M3
MiniMax-M3High
5.4%
Qwen3.5
Qwen3.5
4.2%
Gemma 4 31B
Gemma 4 31B
3.8%
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%

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.