Review: 10 remaining accepted tasks (checklist)

2026-10-03 18:55:25 +02:00
parent 5e3baf43d3
commit 530590f8b3
3 changed files with 50 additions and 0 deletions
--- a/tasks_gen/eval/G0166/empirical.json
+++ b/tasks_gen/eval/G0166/empirical.json
@@ -32,5 +32,21 @@
   "seconds": 93.3,
   "run_dir": "runs/emp/16008_G0166_llm_deepseek-v4.1-flash_cloud"
  }
+ },
+ "deepseek-v4.1-flash:cloud": {
+  "score": 80.0,
+  "parts": {
+   "correctness": 40.0,
+   "craft": 20.0,
+   "clean": 15.0,
+   "own_tests": 0.0,
+   "discipline": 5.0,
+   "total": 80.0,
+   "note": "own_tests: faulty-reference part not implemented in skeleton"
+  },
+  "hidden": "8/8",
+  "tool_calls": 25,
+  "seconds": 240.5,
+  "run_dir": "runs/emp/18004_G0166_llm_deepseek-v4.1-flash_cloud"
 }
 }