Additional-owner OwnerSync write-back coverage auditCustomer & Account Analytics
How each model performed on this task. Every chart states its N, and the reward carries a 95% confidence interval once there is more than one trial to measure.
Core metrics
Check Pass %
Mean share of the task's checks passing, averaged over trials. N = 10 trials per model.
97%
GPT-5.5
75%
Claude Opus 4.8
53%
Gemini 3.1 Pro
23%
Gemini 3.5 Flash
Extended metrics
Median Time
Wall-clock minutes, median across trials. N = 10 trials per model.
7m
Gemini 3.1 Pro
5m
Gemini 3.5 Flash
3m
GPT-5.5
2m
Claude Opus 4.8
Tool Calls
Tool invocations, median across trials — counted from the trajectories. N = 10 trials per model.
41
GPT-5.5
38
Gemini 3.1 Pro
35
Gemini 3.5 Flash
21
Claude Opus 4.8
Verifier × model pass rate
How often each verifier passed, per model. Green is passing, red is failing — a red band across a row is a verifier nothing clears.
| Verifier | GPT-5.5n=10 | Claude Opus 4.8n=10 | Gemini 3.1 Pron=10 | Gemini 3.5 Flashn=10 |
|---|---|---|---|---|
| checks (12) | ||||
| answer_approved_and_kyc_coverage | 90% | 20% | 10% | 20% |
| answer_new_owner_write_coverage | 100% | 100% | 90% | 40% |
| answer_owner_add_apps_total | 100% | 100% | 100% | 80% |
| deliverable_jira_ticket_filed | 100% | 100% | 20% | 0% |
| deliverable_slack_channel_exists | 100% | 100% | 90% | 0% |
| deliverable_slack_message_content | 90% | 30% | 10% | 0% |
| floor_all_connectors | 100% | 100% | 90% | 0% |
| floor_read_source_confluence | 0% | 10% | 0% | 70% |
| floor_sql_investigation | 100% | 100% | 100% | 100% |
| floor_write_back | 100% | 100% | 90% | 0% |
| trace_all_connectors_and_trap | 90% | 20% | 10% | 0% |
| trace_ownersync_coverage_method | 90% | 10% | 0% | 0% |