pf02 Platform port
Task 16 / 20
CommonJS → V8 realm
Stylus 0.63.0 CommonJS + Node ESM in a V8 realm
The host the code assumes changes. 16,012 lines, 10 hours per model, and 2,570 checks across 12 modules.
- Runs
- 26
- Past rung 1
- 12
- Past rung 2
- 0
- Past rung 3
- 0
- Best composite
- —
one per configuration
of 26 — the migration happened
of those 12 — every check perfect
no run got this far
nothing scored here
The instrument
Acceptance gates
7
decide whether the migration happened
Behavioral modules
12
ported suites, run against the new tree
Frozen checks
2,570
all must pass to open rung three
Verifiers
6
hostile programs, written against the spec
Where the 26 runs stopped
- 14
- Never migrated
- 12
- Migrated, behavior lost
- 0
- Perfect suite, gate rejected
- 0
- Verifier found a difference
- 0
- Accepted
No run was perfect on all 2,570 checks. No run reached rung three, so no verifier was paid to attack this task.
By model
| Model | Runs | Gate | Ceil. | Where they stopped | Mean | Best |
|---|---|---|---|---|---|---|
| claude-opus-5 | 5 | 5 | 0 | | 0.0 | — |
| claude-sonnet-5 | 5 | 4 | 0 | | 0.0 | — |
| dsv4-flash | 1 | 1 | 0 | | 0.0 | — |
| glm-5.2 | 1 | 0 | 0 | | 0.0 | — |
| gpt-5.6-luna | 6 | 2 | 0 | | 0.0 | — |
| gpt-5.6-sol | 6 | 0 | 0 | | 0.0 | — |
| kimi-k3 | 1 | 0 | 0 | | 0.0 | — |
| qwen3.8-max | 1 | 0 | 0 | | 0.0 | — |
Every run
best composite firstOne row per configuration. Shape is the run's tool sequence in 24 slices — pale is shell, dark is an edit — and each log is the full session as recorded.
| Model | Effort | Outcome | Gate | Checks | Verif. | Score | Shape |
|---|---|---|---|---|---|---|---|
| gpt-5.6-luna | none | failed | 3/7 | 99.9% | — | 0 | |
| qwen3.8-max | max | failed | 3/7 | 99.9% | — | 0 | |
| claude-opus-5 | xhigh | partial | 7/7 | 57.5% | — | 0 | |
| claude-opus-5 | medium | partial | 7/7 | 57.5% | — | 0 | |
| claude-opus-5 | high | partial | 7/7 | 57.5% | — | 0 | |
| claude-opus-5 | max | partial | 7/7 | 57.5% | — | 0 | |
| glm-5.2 | max | failed | 6/7 | 57.4% | — | 0 | |
| gpt-5.6-sol | max | failed | 6/7 | 57.4% | — | 0 | |
| dsv4-flash | max | partial | 7/7 | 57.3% | — | 0 | |
| claude-opus-5 | low | partial | 7/7 | 57.2% | — | 0 | |
| claude-sonnet-5 | xhigh | partial | 7/7 | 57.2% | — | 0 | |
| gpt-5.6-luna | max | partial | 7/7 | 56.4% | — | 0 | |
| gpt-5.6-sol | xhigh | failed | 5/7 | 56.3% | — | 0 | |
| gpt-5.6-luna | xhigh | partial | 7/7 | 55.4% | — | 0 | |
| claude-sonnet-5 | high | partial | 7/7 | 54.0% | — | 0 | |
| claude-sonnet-5 | low | failed | 6/7 | 53.4% | — | 0 | |
| gpt-5.6-luna | low | failed | 4/7 | 50.7% | — | 0 | |
| gpt-5.6-luna | high | failed | 6/7 | 50.4% | — | 0 | |
| gpt-5.6-luna | medium | failed | 6/7 | 50.2% | — | 0 | |
| gpt-5.6-sol | medium | failed | 5/7 | 50.0% | — | 0 | |
| gpt-5.6-sol | none | failed | 6/7 | 50.0% | — | 0 | |
| gpt-5.6-sol | high | failed | 6/7 | 49.8% | — | 0 | |
| gpt-5.6-sol | low | failed | 4/7 | 41.4% | — | 0 | |
| claude-sonnet-5 | max | partial | 7/7 | 40.2% | — | 0 | |
| kimi-k3 | max | failed | 5/7 | 36.0% | — | 0 | |
| claude-sonnet-5 | medium | partial | 7/7 | 33.6% | — | 0 |