HealthBench Professional

GPT-6 Astra
GPT-6 AstraMax
64.5%
GPT-6.1 Sol
GPT-6.1 SolMax
64.4%
Sonnet 5.5
Sonnet 5.5Max
62.7%
GPT-6 Luna
GPT-6 LunaMax
62.2%
GPT-6 Sol
GPT-6 SolMax
61.4%
GPT-5.6 Sol
GPT-5.6 SolMax • Pro
61.4%
Opus 5.5
Opus 5.5Max
60.4%
Fable 5
Fable 5Max
59.0%
Haiku 5.5
Haiku 5.5Max
58.8%
Muse Spark Open
Muse Spark OpenxHigh
57.2%
Fable 5.1
Fable 5.1Max
56.5%
GPT-5.6 Terra
GPT-5.6 TerraMax
56.3%
Grok 4.7
Grok 4.7xHigh
56.2%
GPT-5.6 Luna
GPT-5.6 LunaMax
55.9%
Opus 5
Opus 5Max
55.4%
Gemini 4 Argon
Gemini 4 ArgonHigh
55.4%
GLM-5.3
GLM-5.3Max
52.9%
Sonnet 5
Sonnet 5Max
52.5%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
52.4%
GPT-5.5
GPT-5.5xHigh
51.2%
Kimi K3
Kimi K3Max
50.2%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
49.9%
Opus 4.7
Opus 4.7Max
49.7%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
48.4%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
46.4%
Grok 4.6
Grok 4.6xHigh
44.4%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
43.9%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
43.4%
Grok 4.5
Grok 4.5High
42.5%
Beam
BeamMax
41.7%
Inkling
InklingHigh
41.2%
DeepSeek-V4-Pro-0813
DeepSeek-V4-Pro-0813Max
40.9%
Qwen3.8-Max
Qwen3.8-MaxxHigh
39.0%
MiniMax-M3
MiniMax-M3High
37.1%
Gemini 3.5 Flash Lite
Gemini 3.5 Flash LiteHigh
35.0%
Nemotron 3 Ultra
Nemotron 3 UltraHigh
32.9%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
32.8%
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.