DeepSWE v1.1

Opus 5.5
Opus 5.5Max
72.3%
GPT-6.1 Sol
GPT-6.1 SolMax
72.3%
GPT-6 Astra
GPT-6 AstraMax
72.0%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
71.7%
Opus 5
Opus 5Max
71.4%
Gemini 3.8 Flash
Gemini 3.8 FlashHigh
71.4%
GLM-5.3
GLM-5.3Max
70.5%
GPT-5.6 Sol
GPT-5.6 SolMax
70.5%
GPT-6 Sol
GPT-6 SolMax
70.5%
Sonnet 5.5
Sonnet 5.5Max
70.5%
GPT-5.6 Terra
GPT-5.6 TerraMax
70.2%
Fable 5
Fable 5Max
67.3%
Fable 5.1
Fable 5.1High
67.3%
GPT-6 Luna
GPT-6 LunaMax
67.0%
Kimi K3
Kimi K3Max
66.4%
GPT-5.5
GPT-5.5xHigh
66.1%
Gemini 3.7 Flash
Gemini 3.7 FlashHigh
65.5%
GPT-5.6 Luna
GPT-5.6 LunaMax
64.3%
Grok 4.6
Grok 4.6High
63.7%
Haiku 5.5
Haiku 5.5Max
59.9%
Opus 4.8
Opus 4.8Max
59.6%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
56.6%
DeepSeek-V4-Pro-0813
DeepSeek-V4-Pro-0813Max
56.3%
Qwen3.8-Max
Qwen3.8-MaxxHigh
53.1%
Sonnet 5
Sonnet 5Max
49.6%
Grok 4.5
Grok 4.5High
49.3%
Opus 4.7
Opus 4.7Max
49.3%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
49.3%
GPT-5.4
GPT-5.4xHigh
49.0%
GLM-5.3-Flash
GLM-5.3-FlashMax
42.5%
Muse Spark 1.1
Muse Spark 1.1xHigh
40.4%
GLM-5.2
GLM-5.2Max
38.9%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
36.6%
Sonnet 4.6
Sonnet 4.6High
34.2%
Grok 4.7
Grok 4.7xHigh
33.3%
Opus 4.6
Opus 4.6Max
31.9%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
30.1%
Muse Spark 1.3
Muse Spark 1.3Max
23.0%
Muse Spark 1.2
Muse Spark 1.2xHigh
21.5%
GLM-5.1
GLM-5.1
18.9%
MiniMax-M3
MiniMax-M3High
9.1%
DeepSeek-V4-Pro
DeepSeek-V4-ProMax
9.1%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
7.7%
Inkling
InklingHigh
5.0%
GLM-5
GLM-5Thinking
2.1%
DeepSeek-V3.2
DeepSeek-V3.2
0.6%
Nemotron 3 Ultra
Nemotron 3 UltraHigh
0.6%
GPT-OSS-120B
GPT-OSS-120BHigh
0.0%
Kimi K2
Kimi K2High • Thinking
0.0%
MiniMax-M2.7
MiniMax-M2.7High
0.0%
Qwen3.5
Qwen3.5
0.0%
Gemma 4 31B
Gemma 4 31B
0.0%
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.