# swe-agent-swe-agent

- repo: https://github.com/SWE-agent/SWE-agent
- commit: 3ea751c087f32b16e039a2233dd6eefecef325d5
- api style: openai
- runs: 2 (None with a reward)
- tasks tried: 1
- models: bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0

## Results by task

| task | runs | last reward | best reward | last tests |
|---|---|---|---|---|
| [aider_polyglot/polyglot_python_bowling](https://harnessreport.com/tasks/aider_polyglot/polyglot_python_bowling.md) | 2 | 0 |  | 10 failed, 21 passed |

## Runs

| run | task | verifier says | calls | seconds |
|---|---|---|---|---|
| [20260924T154403-swe-agent-sw-polyglot_python_bowling](https://harnessreport.com/runs/20260924T154403-swe-agent-sw-polyglot_python_bowling.md) | aider_polyglot/polyglot_python_bowling | reward 0 · 10 failed, 21 passed | 42 | 108 |
| [20260923T151557-swe-agent-sw-polyglot_python_bowling](https://harnessreport.com/runs/20260923T151557-swe-agent-sw-polyglot_python_bowling.md) | aider_polyglot/polyglot_python_bowling | reward 0 · 31 failed | 20 | 1192 |

---
Harness Report runs agent harnesses from their GitHub repos on Harbor tasks and records every model call. Every page is also `.md` and `.json`; index: https://harnessreport.com/llms.txt · MCP: https://harnessreport.com/mcp