SWE Atlas - Codebase QnA Extended

Sonnet 5.5
Sonnet 5.5Max
44.7%
Opus 5.5
Opus 5.5Max
43.3%
Opus 5
Opus 5Max
40.0%
Fable 5.1
Fable 5.1Max
38.0%
DeepSeek-V4.1-Flash
DeepSeek-V4.1-FlashMax
36.7%
Qwen3.8-Max
Qwen3.8-MaxxHigh
33.3%
Sonnet 5
Sonnet 5Max
32.7%
GPT-6.1 Sol
GPT-6.1 SolMax
31.3%
GPT-6 Sol
GPT-6 SolMax
31.3%
GPT-5.6 Sol
GPT-5.6 SolMax • Pro
24.7%
Kimi K3
Kimi K3Max
24.0%
Opus 4.8
Opus 4.8Max
24.0%
Grok 4.6
Grok 4.6xHigh
19.3%
GPT-5.6 Luna
GPT-5.6 LunaMax
19.3%
DeepSeek-V4-Flash
DeepSeek-V4-FlashMax
18.0%
GPT-5.5
GPT-5.5xHigh
17.3%
GLM-5.2
GLM-5.2Max
16.0%
GPT-5.6 Terra
GPT-5.6 TerraMax
16.0%
Grok 4.7
Grok 4.7xHigh
15.3%
GPT-6 Luna
GPT-6 LunaMax
15.3%
Grok 4.5
Grok 4.5High
12.0%
Opus 4.7
Opus 4.7Max
11.3%
GPT-5.4
GPT-5.4xHigh
10.7%
MiniMax-M3
MiniMax-M3High
10.0%
Sonnet 4.6
Sonnet 4.6High
6.7%
DeepSeek-V4-Pro
DeepSeek-V4-ProMax
5.3%
Muse Spark Open
Muse Spark OpenxHigh
5.0%
Kimi K2.7 Code
Kimi K2.7 CodeHigh
4.7%
Gemini 3.6 Flash
Gemini 3.6 FlashHigh
4.7%
Gemini 3.5 Flash
Gemini 3.5 FlashHigh
2.7%
Gemini 3.1 Pro
Gemini 3.1 ProHigh
2.7%
Inkling
InklingHigh
1.3%
Fable 5
Fable 5Max
0.0%
DeepSeek-V3.2
DeepSeek-V3.2
0.0%
0%
10%
20%
30%
40%
50%
60%
70%

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.