Reg CC large-deposit exception (aggregate-per-banking-day) hold exposureCompliance & Regulatory
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.
53%
Gemini 3.1 Pro
52%
Claude Opus 4.8
42%
GPT-5.5
0%
Gemini 3.5 Flash
Extended metrics
Median Time
Wall-clock minutes, median across trials. N = 10 trials per model.
2m
Gemini 3.5 Flash
2m
GPT-5.5
2m
Gemini 3.1 Pro
1m
Claude Opus 4.8
Tool Calls
Tool invocations, median across trials — counted from the trajectories. N = 10 trials per model.
22
Gemini 3.5 Flash
21
GPT-5.5
21
Gemini 3.1 Pro
11
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 (7) | ||||
| cp1_large_deposit_count | 0% | 10% | 40% | 0% |
| cp2_total_excess_held_usd | 0% | 10% | 40% | 0% |
| cp3_avg_days_to_available | 50% | 80% | 10% | 0% |
| deliverable_slack_channel_exists | 100% | 100% | 100% | 0% |
| deliverable_slack_message_pinned | 100% | 100% | 100% | 0% |
| rubric_slack_message_completeness | 0% | 10% | 30% | 0% |
| rubric_aggregate_availability_and_datefield | 0% | 0% | 0% | 0% |
Failure modes on this task
39 tagged verifier failures, by the stage they were assigned to. Higher is worse.
| Failure stage | GPT-5.5 | Claude Opus 4.8 | Gemini 3.1 Pro | Gemini 3.5 Flash |
|---|---|---|---|---|
| Answer1 mode | 10 | 9 | 10 | 10 |