Auditable DeepSWE v1.1 evaluation of Agent Claim Network: coding-harness pass rate and cross-agent claim reuse｜ACN 在 DeepSWE v1.1 上的可复现评测：coding harness 通过率与跨 agent 的 claim 复用收益。
-
Updated
Sep 17, 2026 - Python
#
deepswe
Here are 7 public repositories matching this topic...
Public evidence for AIC coding-agent evaluations: frozen patches, canonical verifier scores, integrity hashes, cost, timing, and task context.
benchmark evaluation software-engineering reproducibility ai-agents qwen llm-evaluation coding-agents deepswe deep-swe
-
Updated
Sep 27, 2026 - PowerShell
DeepSWE v1.1: Perfect score (113/113) — all tasks solved with reward=1.0
-
Updated
Aug 13, 2026 - Python
Reproducible analysis of reasoning-effort saturation on DeepSWE v1.1
-
Updated
Aug 22, 2026 - Python
DeepSWE Launcher ⚡ lightweight DeepSWE benchmark launcher: batching, resume, multi-model profiles, live dashboard (terminal + WebUI), Excel reports
python resume benchmark dashboard webui excel-report pier llm-evaluation coding-agent swe-bench evaluation-harness task-orchestrator deepswe pass-at-1
-
Updated
Sep 1, 2026 - Python
Forensic audit scanner for SWE-bench & DeepSWE v1.1 containers detecting .git reflog leakage and test harness spoofing.
-
Updated
Sep 21, 2026 - Python
Daily mirror of the DeepSWE live leaderboard with TrueIQ benchmarking analysis.
-
Updated
Sep 29, 2026 - Python
Add this topic to your repo
To associate your repository with the deepswe topic, visit your repo's landing page and select "manage topics."