Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Coding on SWE-Bench Pro (public)
Loading...
69.1
Solve Rate
Claude Opus 4.7
44.868
51.159
57.45
63.741
Jun 11, 2026
Solve Rate
Average Cost per Instruction ($)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Solve Rate
Average Cost per Instruction ($)
Claude Opus 4.7
Harness=Claude Code, T...
2026.06
69.1
2.28
GPT-5.4
Harness=Codex, Thinkin...
2026.06
62.1
1.41
Gemini 3.1 Pro
Harness=OpenCode, Thin...
2026.06
54.4
0.97
Qwen3.5-397B-A17B
Harness=MSA, Thinking=...
2026.06
45.8
-
Feedback
Search any
task
Search any
task