Find the best in-ground or portable basketball hoopSports
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
71%
Claude Opus 5.5
43%
GPT-6 sol
43%
GPT-5.6 sol
Extended metrics
Median Time
Wall-clock minutes, median across runs. N = 1 run per model.
29m
Claude Opus 5
17m
GPT-5.6 sol
Tool Calls
Tool invocations, median across runs — counted from the trajectories. N = 1 run per model.
89
Claude Opus 5
53
Claude Opus 5.5
35
GPT-5.6 sol
32
GPT-6 sol
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 (7) | ||||
| 100% | 0% | 100% | 100% | |
How to passUse the stated 20 ft of clearance and $600 budget, and compare whether each system's published installation requirements are compatible with the stated space. Flag any site-specific in-ground requirement that cannot be verified remotely. | ||||
| 100% | 100% | 0% | 100% | |
How to passGo to https://www.spalding.com/, shortlist a system matching the budget, and record backboard size/material, any stated rim type (or note that the page does not specify one), and price. | ||||
| 100% | 100% | 100% | 100% | |
How to passGo to https://www.goalrilla.com/, shortlist a comparable system, and record the same details. | ||||
| 100% | 100% | 100% | 100% | |
How to passGo to https://www.dickssportinggoods.com/, search for comparable systems (may include other brands), and record the same details plus availability. | ||||
| 0% | 0% | 0% | 100% | |
How to passFor each shortlisted option, note whether professional installation is recommended/required and any additional cost for concrete anchoring (in-ground) versus a fillable base (portable). | ||||
| 0% | 0% | 0% | 100% | |
How to passCompare backboard material (acrylic vs. polycarbonate vs. tempered glass) for weather resistance and rebound quality. | ||||
| 100% | 0% | 0% | 100% | |
How to passProduce a table with columns: System, Backboard size/material, Rim type, Install type, Price, then state the top pick with reasoning. | ||||
Failure modes on this task
10 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 | — | 2 | 2 | — |
| Standing up the evidence1 mode | 2 | 1 | — | — |
| No signal in the judge’s words1 mode · the grader | — | 1 | 2 | — |