Monthly snapshot ledger continuity auditReconciliation & Settlement
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.
88%
GPT-5.5
58%
Claude Opus 4.8
37%
Gemini 3.5 Flash
25%
Gemini 3.1 Pro
Extended metrics
Median Time
Wall-clock minutes, median across trials. N = 10 trials per model.
42m
Gemini 3.5 Flash
2m
GPT-5.5
2m
Claude Opus 4.8
2m
Gemini 3.1 Pro
Tool Calls
Tool invocations, median across trials — counted from the trajectories. N = 10 trials per model.
91
Gemini 3.5 Flash
18
GPT-5.5
16
Gemini 3.1 Pro
15
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_cluster_2023_08_count | 80% | 40% | 0% | 50% |
| answer_continuity_break_counts | 80% | 40% | 0% | 60% |
| answer_rollover_population_and_incomplete_count | 80% | 40% | 0% | 60% |
| deliverable_jira_ticket_filed | 100% | 90% | 50% | 20% |
| deliverable_slack_channel_exists | 100% | 100% | 100% | 20% |
| deliverable_slack_message_content | 90% | 40% | 0% | 10% |
| deliverable_slack_message_pinned | 100% | 100% | 100% | 20% |
| floor_read_source_page | 100% | 100% | 100% | 100% |
| floor_sql_investigation | 100% | 100% | 100% | 100% |
| floor_write_back | 100% | 90% | 40% | 20% |
| trace_break_classification_and_scope | 90% | 100% | 90% | 40% |
| trace_snapshot_chaining_method | 80% | 90% | 80% | 60% |