Eval Report: ci-pr-smoke

Profile: gdm-swebench-lite-v1 | Tasks: 15 | Pass rate: 100.0% | Cost: $0.1500

Task IDBandScorePassedCost
python-bugfix-easy-001easy0.740$0.0100
python-config-easy-001easy0.740$0.0100
python-dependency-easy-001easy0.740$0.0100
python-explain-easy-001easy0.740$0.0100
python-multi-file-easy-001easy0.740$0.0100
python-performance-easy-001easy0.740$0.0100
python-recovery-easy-001easy0.740$0.0100
python-refactor-easy-001easy0.740$0.0100
python-security-fix-easy-001easy0.740$0.0100
python-test-writing-easy-001easy0.740$0.0100
typescript-bugfix-easy-001easy0.740$0.0100
typescript-config-easy-001easy0.740$0.0100
typescript-dependency-easy-001easy0.740$0.0100
typescript-explain-easy-001easy0.740$0.0100
typescript-multi-file-easy-001easy0.740$0.0100

Leaderboard Snapshot

Latest run: 5387e7ff-f431-4d2f-9295-4c7936a4e2b9 | Latest model: coder | Latest score: 0.740 | Recorded at: 2026-04-26T08:30:15.211289+00:00

Recent Trend

Run IDModelGit SHAScoreCreated
5387e7ff-f431-4d2f-9295-4c7936a4e2b9coder4669773b4fbe9d507f1396f38777a1b36998faf30.7402026-04-26T08:30:15.211289+00:00
d139845f-96b9-493c-b9ea-9cb4baf0af28coder4669773b4fbe9d507f1396f38777a1b36998faf30.7402026-04-26T08:30:15.148858+00:00
0291a749-d902-4f5e-8778-5b74ae2a5103coder4669773b4fbe9d507f1396f38777a1b36998faf30.7402026-04-26T08:30:15.052915+00:00
2451080c-9b37-48d3-a23c-295a31c6959acoder4669773b4fbe9d507f1396f38777a1b36998faf30.7402026-04-26T08:30:14.975537+00:00
08e4481d-4895-4bc9-a00f-5b7231b9d792coder4669773b4fbe9d507f1396f38777a1b36998faf30.7402026-04-26T08:30:14.833053+00:00

Cost Frontier

pass_rate vs cost_usd (Pareto frontier marked with *)
* [####################] 100.0% @ $0.0100  (coder)