Empirical filter results: DeepSeek reruns W6A/W7A (partial)

2026-10-03 18:54:16 +02:00
parent d83a39a8d8
commit 5e3baf43d3
13 changed files with 210 additions and 0 deletions
--- a/tasks_gen/eval/G0158/empirical.json
+++ b/tasks_gen/eval/G0158/empirical.json
@@ -16,5 +16,21 @@
   "seconds": 52.5,
   "run_dir": "runs/emp/11028_G0158_llm_deepseek-v4.1-flash_cloud"
  }
+ },
+ "deepseek-v4.1-flash:cloud": {
+  "score": 85.0,
+  "parts": {
+   "correctness": 40.0,
+   "craft": 20.0,
+   "clean": 15.0,
+   "own_tests": 0.0,
+   "discipline": 10.0,
+   "total": 85.0,
+   "note": "own_tests: faulty-reference part not implemented in skeleton"
+  },
+  "hidden": "11/11",
+  "tool_calls": 14,
+  "seconds": 58.9,
+  "run_dir": "runs/emp/18001_G0158_llm_deepseek-v4.1-flash_cloud"
 }
 }