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/G0170/empirical.json
+++ b/tasks_gen/eval/G0170/empirical.json
@@ -14,5 +14,19 @@
   "seconds": 73.6,
   "run_dir": "runs/emp/12018_G0170_llm_deepseek-v4.1-flash_cloud"
  }
+ },
+ "deepseek-v4.1-flash:cloud": {
+  "score": 0,
+  "parts": {
+   "total": 0,
+   "stop": "implemented",
+   "objects": [
+    "Z0D4E04Q_STUDIO_PRICER"
+   ]
+  },
+  "hidden": "0/0",
+  "tool_calls": 11,
+  "seconds": 80.3,
+  "run_dir": "runs/emp/17006_G0170_llm_deepseek-v4.1-flash_cloud"
 }
 }