CX outbound-wire reconcilePayments & Transfers
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.
100%
Claude Opus 4.8
93%
GPT-5.5
63%
Gemini 3.1 Pro
37%
Gemini 3.5 Flash
Extended metrics
Median Time
Wall-clock minutes, median across trials. N = 10 trials per model.
11m
Gemini 3.5 Flash
4m
Claude Opus 4.8
2m
GPT-5.5
1m
Gemini 3.1 Pro
Tool Calls
Tool invocations, median across trials — counted from the trajectories. N = 10 trials per model.
68
Claude Opus 4.8
50
Gemini 3.5 Flash
25
GPT-5.5
12
Gemini 3.1 Pro
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_outbound_wire_notifications | 100% | 100% | 50% | 50% |
| cp2_cx_squad_wire_mentions | 80% | 100% | 40% | 0% |
| deliverable_freshdesk_ticket | 100% | 100% | 100% | 60% |
| process_floor | 60% | 30% | 0% | 60% |
Failure modes on this task
18 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 | 2 | n/a | 6 | 10 |
Claude Opus 4.8 failed checks on this task that carry no failure mode, so its column reads n/a