SciCode

Opus 5.5
Opus 5.5Max
57.4%
Fable 5.1
Fable 5.1Max
54.6%
Fable 5
Fable 5Max
52.6%
Sonnet 5.5
Sonnet 5.5Max
51.2%
GPT-6 Astra
GPT-6 AstraxHigh
49.3%
Opus 5
Opus 5Max
48.1%
GPT-5.6 Sol
GPT-5.6 SolxHigh
47.8%
Opus 4.8
Opus 4.8Max
47.6%
Muse Wonder 1.0
Muse Wonder 1.0Max
47.4%
GPT-5.4
GPT-5.4xHigh
47.3%
Opus 4.7
Opus 4.7Max
47.1%
Kimi K3
Kimi K3Max
46.9%
Muse Spark Open
Muse Spark OpenxHigh
46.9%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
46.6%
GPT-6.1 Sol
GPT-6.1 SolMax
46.5%
GPT-6 Luna
GPT-6 LunaMax
46.0%
GPT-6 Sol
GPT-6 SolMax
45.8%
Grok 4.6
Grok 4.6xHigh
45.6%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
45.4%
GPT-5.5
GPT-5.5xHigh
45.4%
Grok 4.5
Grok 4.5High
45.2%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
44.6%
GPT-5.6 Terra
GPT-5.6 TerraMax
44.1%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
43.3%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
43.1%
Qwen3.8-Max
Qwen3.8-MaxxHigh
42.3%
GPT-5.6 Luna
GPT-5.6 LunaMax
42.3%
Haiku 5.5
Haiku 5.5Max
41.8%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
41.8%
GLM-5.2
GLM-5.2Max
41.3%
Beam
BeamMax
41.2%
DeepSeek-V4-Pro
DeepSeek-V4-ProMax
40.8%
Gemma 4 31B
Gemma 4 31B
39.5%
MiniMax-M3
MiniMax-M3High
39.1%
Inkling
InklingHigh
38.8%
Sonnet 4.6
Sonnet 4.6High
37.6%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
37.5%
MiniMax-M2.7
MiniMax-M2.7High
35.3%
Kimi K2
Kimi K2High • Thinking
34.9%
DeepSeek-V3.2
DeepSeek-V3.2
34.1%
GPT-OSS-120B
GPT-OSS-120BHigh
31.4%
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.