I'm planning a solo trip to Florida's EastTravel and Tourism
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 run to measure.
Core metrics
Check Pass %
Mean share of the task's checks passing, averaged over runs. N = 1 run per model.
100%
Claude Opus 5.5
83%
GPT-5.6 sol
83%
Claude Opus 5
67%
GPT-6 sol
Extended metrics
Median Time
Wall-clock minutes, median across runs. N = 1 run per model.
9m
Claude Opus 5
7m
GPT-5.6 sol
Tool Calls
Tool invocations, median across runs — counted from the trajectories. N = 1 run per model.
37
Claude Opus 5
31
GPT-6 sol
16
GPT-5.6 sol
15
Claude Opus 5.5
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 | Claude Opus 5.5n=1 | GPT-6 soln=1 | GPT-5.6 soln=1 | Claude Opus 5n=1 |
|---|---|---|---|---|
| checks (6) | ||||
| 100% | 100% | 100% | 100% | |
How to passNavigate to https://www.kennedyspacecenter.com/info/tickets and extract the base 1-Day ticket price for an adult | ||||
| 100% | 0% | 100% | 100% | |
How to passNavigate to the official Kennedy Space Center ticketing page and extract the current adult price for the “Chat With An Astronaut” add-on. If the price does not render on the linked page, use another official Kennedy Space Center ticketing or booking page that displays the same add-on and verify the adult price there. | ||||
| 100% | 100% | 100% | 0% | |
How to passNavigate to https://www.visitspacecoast.com/profile/melbourne-beach/accommodations/sebastian-inlet-state-park/ and extract the multiple-occupant vehicle fee | ||||
| 100% | 100% | 100% | 100% | |
How to passNavigate to https://brevardzoo.org/visit/ and extract the "Buy Online & Save" adult ticket price | ||||
| 100% | 100% | 100% | 100% | |
How to passNavigate to https://www.ponceinlet.org/plan-your-visit/admission-rates/ and extract the general adult admission rate | ||||
| 100% | 0% | 0% | 100% | |
How to passSynthesize the findings into a short itinerary document and accurately sum the five extracted prices for the final budget constraint | ||||
Failure modes on this task
4 tagged verifier failures, by the stage they were assigned to. Higher is worse.
| Failure stage | Claude Opus 5.5 | GPT-6 sol | GPT-5.6 sol | Claude Opus 5 |
|---|---|---|---|---|
| Delivering the result1 mode | — | 1 | 1 | — |
| No signal in the judge’s words1 mode · the grader | — | 1 | — | 1 |