Bill goal adoption parityCustomer & Account Analytics
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.
40%
Claude Opus 4.8
30%
GPT-5.5
0%
Gemini 3.1 Pro
0%
Gemini 3.5 Flash
Extended metrics
Median Time
Wall-clock minutes, median across trials. N = 10 trials per model.
67m
Gemini 3.1 Pro
14m
Gemini 3.5 Flash
6m
GPT-5.5
5m
Claude Opus 4.8
Tool Calls
Tool invocations, median across trials — counted from the trajectories. N = 10 trials per model.
116
Gemini 3.1 Pro
83
GPT-5.5
67
Claude Opus 4.8
50
Gemini 3.5 Flash
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) | ||||
| gold_goal_minus_bill_official_adopter_gap | 30% | 40% | 0% | 0% |
| process_confluence_adoption_policy_read | 80% | 70% | 80% | 40% |
| process_jira_funding_context | 70% | 80% | 100% | 50% |
| process_sql | 100% | 100% | 50% | 100% |