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/G0162/empirical.json
+++ b/tasks_gen/eval/G0162/empirical.json
@@ -31,5 +31,20 @@
   "seconds": 587.0,
   "run_dir": "runs/emp/16015_G0162_llm_deepseek-v4.1-flash_cloud"
  }
+ },
+ "deepseek-v4.1-flash:cloud": {
+  "score": 0,
+  "parts": {
+   "total": 0,
+   "failed_gates": [
+    "G1_active",
+    "G2_contract",
+    "G3_hidden_runs"
+   ]
+  },
+  "hidden": "0/0",
+  "tool_calls": 36,
+  "seconds": 510.6,
+  "run_dir": "runs/emp/18002_G0162_llm_deepseek-v4.1-flash_cloud"
 }
 }