Subscription dead invoice rateSubscriptions & Billing
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.
80%
Gemini 3.1 Pro
50%
Gemini 3.5 Flash
40%
GPT-5.5
20%
Claude Opus 4.8
Extended metrics
Median Time
Wall-clock minutes, median across trials. N = 10 trials per model.
5m
Gemini 3.5 Flash
4m
Gemini 3.1 Pro
2m
GPT-5.5
1m
Claude Opus 4.8
Tool Calls
Tool invocations, median across trials — counted from the trajectories. N = 10 trials per model.
62
Gemini 3.5 Flash
41
Gemini 3.1 Pro
15
GPT-5.5
6
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 (3) | ||||
| gold_billed_revenue_collected_share | 40% | 20% | 80% | 50% |
| process_confluence_read | 0% | 0% | 80% | 90% |
| process_sql | 100% | 100% | 100% | 100% |
Failure modes on this task
21 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 |
|---|---|---|---|---|
| Answer2 modes | 6 | 8 | 2 | 5 |