Goal Automation Throughput AnalysisPayments & 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.
96%
Claude Opus 4.8
93%
GPT-5.5
84%
Gemini 3.1 Pro
31%
Gemini 3.5 Flash
Extended metrics
Median Time
Wall-clock minutes, median across trials. N = 10 trials per model.
18m
Gemini 3.5 Flash
3m
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.
66
Gemini 3.5 Flash
21
GPT-5.5
19
Gemini 3.1 Pro
14
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 (19) | ||||
| cp10_pending_on_deleted_automations | 100% | 100% | 90% | 20% |
| cp11_account_concentration | 100% | 100% | 90% | 20% |
| cp12_median_landed | 100% | 100% | 90% | 30% |
| cp13_peak_month_landed | 70% | 100% | 80% | 30% |
| cp14_accounts_for_three_quarters | 100% | 100% | 90% | 20% |
| cp15_peak_month_accounts | 70% | 100% | 80% | 20% |
| cp16_accounts_with_error_and_landed | 50% | 30% | 0% | 20% |
| cp17_accounts_for_90pct | 100% | 100% | 90% | 20% |
| cp18_peak_month_landed_deleted | 70% | 100% | 80% | 20% |
| cp19_landed_from_error_prone_accounts | 100% | 100% | 90% | 20% |
| cp1_fulfilled_count | 100% | 100% | 90% | 90% |
| cp2_success_rate | 100% | 90% | 90% | 30% |
| cp3_throughput | 100% | 100% | 90% | 40% |
| cp4_avg_actual | 100% | 100% | 90% | 40% |
| cp5_peak_year | 100% | 100% | 90% | 30% |
| cp6_pending_in_flight | 100% | 100% | 90% | 30% |
| cp7_partial_shortfall | 100% | 100% | 90% | 40% |
| cp8_fulfilled_shortfall | 100% | 100% | 90% | 40% |
| cp9_landed_from_deleted_automations | 100% | 100% | 90% | 20% |
Failure modes on this task
33 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 | 7 | 7 | 10 | 9 |