SWE Atlas - Codebase QnA Extended

Opus 5
Opus 5Max
40.0%
Sonnet 5
Sonnet 5Max
32.7%
Kimi K3
Kimi K3Max
24.0%
Opus 4.8
Opus 4.8Max
24.0%
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 4.5
Grok 4.5High
12.0%
Opus 4.7
Opus 4.7Max
11.3%
GPT-5.4
GPT-5.4xHigh
10.7%
Sonnet 4.6
Sonnet 4.6High
6.7%
DeepSeek-V4-Pro
DeepSeek-V4-ProMax
5.3%
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.