HLE

GPT-6 Astra
GPT-6 AstraxHigh
55.6%
Fable 5.1
Fable 5.1Max
54.6%
Opus 5
Opus 5Max
53.2%
Fable 5
Fable 5High
51.5%
GPT-5.6 Sol
GPT-5.6 SolMax
47.0%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
47.0%
Kimi K3
Kimi K3Max
46.5%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
46.0%
GPT-5.5
GPT-5.5xHigh
45.9%
GPT-5.6 Terra
GPT-5.6 TerraMax
44.9%
Opus 4.8
Opus 4.8High
44.8%
GPT-5.4
GPT-5.4xHigh
44.1%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
44.1%
Qwen3.8-Max
Qwen3.8-MaxxHigh
42.2%
Opus 4.7
Opus 4.7High
42.2%
Grok 4.5
Grok 4.5High
41.9%
Grok 4.6
Grok 4.6xHigh
41.3%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
41.2%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
40.6%
GLM-5.3
GLM-5.3Max
40.0%
GPT-5.6 Luna
GPT-5.6 LunaMax
39.6%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
39.0%
MiniMax-M3
MiniMax-M3High
37.8%
Sonnet 5
Sonnet 5High
36.3%
Opus 4.6
Opus 4.6Max
35.0%
DeepSeek-V4-Pro
DeepSeek-V4-ProMax
34.4%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
34.0%
GLM-5.3-Flash
GLM-5.3-FlashMax
33.6%
GLM-5.2
GLM-5.2Max
31.7%
GLM-5.1
GLM-5.1
29.4%
Sonnet 4.6
Sonnet 4.6Medium
29.2%
Nemotron 3 Ultra
Nemotron 3 UltraHigh
28.1%
MiniMax-M2.7
MiniMax-M2.7High
27.1%
Inkling
InklingHigh
25.5%
Gemma 4 31B
Gemma 4 31B
23.2%
DeepSeek-V3.2
DeepSeek-V3.2
22.3%
GPT-OSS-120B
GPT-OSS-120BHigh
18.5%
Kimi K2
Kimi K2HighThinking
12.7%
0%
10%
20%
30%
40%
50%
60%
70%
80%

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.