Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Coding on SWE-Bench
Loading...
54.4
Accuracy
LongCat-Flash-Lite
31.936
37.768
43.6
49.432
Jan 29, 2026
Feb 7, 2026
Feb 17, 2026
Feb 27, 2026
Mar 9, 2026
Mar 19, 2026
Mar 29, 2026
Accuracy
Updated 19d ago
Evaluation Results
Method
Method
Links
Accuracy
LongCat-Flash-Lite
Architecture=MoE + NE,...
2026.01
54.4
LongCat-Next
2026.03
43
Gemini 2.5 Flash-Lite
2026.01
41.3
Qwen3-Next-80B-A3B-Instruct
Architecture=MoE, # To...
2026.01
37.6
Qwen3-Next-80B-A3B-Instruct
2026.03
37.6
Kimi-Linear-48B-A3B
Architecture=MoE, # To...
2026.01
32.8
Kimi-Linear-48B-A3B
2026.03
32.8
Feedback
Search any
task
Search any
task