All runs
Failedrun_1003Lumen Health

Lead dedupe agent — iteration #4

Dedupe inbound leads by fuzzy company+contact matching.

Loop
Lead dedupe agent
Trigger
schedule
Rounds
1 / 3
Critic
gemini-2.5-pro
Started
20652d ago

Round 1

Failed11.7s
Claude Code
58
3/6 tests14.6smajor
  • majorbug: Verifier reported failing test case #3.
OpenAI Codex
58
3/6 tests15.1smajor
  • majorbug: Verifier reported failing test case #3.
Local OSS
58
3/6 tests13.5smajor
  • majorbug: Verifier reported failing test case #3.