Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Coding Agent Capacity on SWE-Lancer
Loading...
56.1
Score
Claude-Opus-4.5
42.58
46.09
49.6
53.11
Jun 30, 2026
Score
Updated 24d ago
Evaluation Results
Method
Method
Links
Score
Claude-Opus-4.5
2026.06
56.1
Gemini-3-Flash High
2026.06
51.7
Seed2.0 Pro
2026.06
49.4
GPT-5.2 High
2026.06
48.9
Seed2.0 Lite
2026.06
47.1
Claude-Sonnet-4.5
2026.06
45.7
Gemini-3-pro High
2026.06
44.3
GPT-5-mini High
2026.06
43.1
Feedback
Search any
task
Search any
task