todo-app-scaffolded · cc-opus-5.5
claude-code · started 2026-10-07T15:26:35.001Z · horizon 480s · judge ai (anthropic:claude-sonnet-5), 2 frames scored
Area under curve
0.956
headline, 0-1
First render
21.2s
anything on screen
First reviewable
21.2s
worth feedback
Final score
1.00
no regression
Correctness over time
Where the time went
99%
Model thinking 25.7sTool round trips 0.2s
| Phase | Time | Share | Side |
|---|---|---|---|
| Model thinking | 25.7s | 99.3% | agent |
| Tool round trips | 0.2s | 0.7% | agent |
| Dependency install | 0.0s | 0.0% | toolchain |
| Build | 0.0s | 0.0% | toolchain |
| Dev server boot | 0.0s | 0.0% | toolchain |
| First paint | 0.0s | 0.0% | toolchain |
| Unaccounted | 0.0s | 0.0% | unknown |
| Wall clock (cold start) | 25.9s | 100% |
Agent or toolchain
100%
Agent (model + tool round trips) 25.9s
Toolchain (install + build + boot + paint) 0.0s
Unaccounted 0.0s
Accounted for: 100.0% of wall clock. Agent reported 28.6s of API time; this run attributed 25.7s (delta 2.9s).
- Excludes 15.0s of deliberate idle observation (settle window); the curve still covers it.
Iteration: prompt to visible change
Follow-ups were injected into the same live session.
| Edit | First visible change | Correct change | Agent done | Tool calls | After agent | Broken for |
|---|---|---|---|---|---|---|
| Make the header background blue. | 4.8s | 4.8s | 9.5s | 0 | -4.8s | -- |
| Add a fourth column called "Blocked" after Done. | 9.0s | 9.0s | 18.3s | 2 (Bash, Edit) | -9.3s | -- |
Judged frames
All brief requirements met with a clean, well-structured, styled task board.
Fully styled task board meeting all brief requirements clearly visible in screenshot.
Caveats
- 1 poll ticks were skipped because a capture overran the interval.
- judge: anthropic:claude-sonnet-5 does not accept a sampling temperature, so these frames were scored at the provider's default rather than at 0. Two runs of the same page can be scored differently, and that variance is inside the AUC. result.json records the temperature as null rather than as the value that was asked for, so p2p compare will not pool this run with one that was scored at a fixed temperature.