Eval Report: ci-pr-smoke

Profile: gdm-swebench-lite-v1 | Tasks: 15 | Pass rate: 100.0% | Cost: $0.0150

Task IDBandScorePassedCost
python-bugfix-easy-001easy0.740$0.0010
python-config-easy-001easy0.740$0.0010
python-dependency-easy-001easy0.740$0.0010
python-explain-easy-001easy0.740$0.0010
python-multi-file-easy-001easy0.740$0.0010
python-performance-easy-001easy0.740$0.0010
python-recovery-easy-001easy0.740$0.0010
python-refactor-easy-001easy0.740$0.0010
python-security-fix-easy-001easy0.740$0.0010
python-test-writing-easy-001easy0.740$0.0010
typescript-bugfix-easy-001easy0.740$0.0010
typescript-config-easy-001easy0.740$0.0010
typescript-dependency-easy-001easy0.740$0.0010
typescript-explain-easy-001easy0.740$0.0010
typescript-multi-file-easy-001easy0.740$0.0010

Leaderboard Snapshot

Latest run: 9dfef11e-b84c-4b80-90bc-66c399bc5e5c | Latest model: coder | Latest score: 0.740 | Recorded at: 2026-04-27T01:06:07.555181+00:00

Recent Trend

Run IDModelGit SHAScoreCreated
9dfef11e-b84c-4b80-90bc-66c399bc5e5ccoder4669773b4fbe9d507f1396f38777a1b36998faf30.7402026-04-27T01:06:07.555181+00:00
c5bc4ec3-32cc-446d-a689-65135d447fd3coder4669773b4fbe9d507f1396f38777a1b36998faf30.7402026-04-27T01:06:07.497579+00:00
f1e2f48e-535c-41b8-9073-0b0597b589decoder4669773b4fbe9d507f1396f38777a1b36998faf30.7402026-04-27T01:06:07.427260+00:00
d78a57e6-e85b-4013-ba3c-438a2156043fcoder4669773b4fbe9d507f1396f38777a1b36998faf30.7402026-04-27T01:06:07.369169+00:00
a618df4f-6ae0-4803-830d-7e8fc4da8648coder4669773b4fbe9d507f1396f38777a1b36998faf30.7402026-04-27T01:06:07.307217+00:00

Cost Frontier

pass_rate vs cost_usd (Pareto frontier marked with *)
* [####################] 100.0% @ $0.0076  (coder)