Confluence Overdraft & NSF PolicyRisk & Fraud
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.
93%
Gemini 3.1 Pro
78%
GPT-5.5
73%
Gemini 3.5 Flash
70%
Claude Opus 4.8
Extended metrics
Median Time
Wall-clock minutes, median across trials. N = 10 trials per model.
13m
GPT-5.5
5m
Gemini 3.1 Pro
4m
Gemini 3.5 Flash
4m
Claude Opus 4.8
Tool Calls
Tool invocations, median across trials — counted from the trajectories. N = 10 trials per model.
290
GPT-5.5
69
Gemini 3.1 Pro
52
Gemini 3.5 Flash
50
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 (4) | ||||
| cp1_overdraft_offered | 100% | 100% | 100% | 80% |
| cp2_negative_balance_count | 100% | 100% | 100% | 80% |
| cp3_healing_attempts | 60% | 30% | 80% | 80% |
| cp4_payday_nsf_transfers | 50% | 50% | 90% | 50% |