Navers lab
← All tasks
fw07 Framework rewrite Task 14 / 20

Dropwizard → Spring Boot

GraphHopper 11.0 Dropwizard 4 Spring Boot 3.5

The language stays, the framework it is organized around is replaced. 94,766 lines, 16 hours per model, and 113 checks across 11 modules.

Runs
26

one per configuration

Past rung 1
9

of 26 — the migration happened

Past rung 2
0

of those 9 — every check perfect

Past rung 3
0

no run got this far

Best composite

nothing scored here

The instrument

Acceptance gates

7

decide whether the migration happened

Behavioral modules

11

ported suites, run against the new tree

Frozen checks

113

all must pass to open rung three

Verifiers

6

hostile programs, written against the spec

Where the 26 runs stopped

15
Never migrated
9
Migrated, behavior lost
2
Perfect suite, gate rejected
0
Verifier found a difference
0
Accepted

2 runs were perfect on all 113 checks and rejected anyway — the migration had not happened. 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 2 0
0.0
dsv4-flash 1 0 0
0.0
glm-5.2 1 1 0
0.0
gpt-5.6-luna 6 0 2
0.0
gpt-5.6-sol 6 1 0
0.0
kimi-k3 1 0 0
0.0
qwen3.8-max 1 0 0
0.0

Every run

best composite first

One 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.

ModelEffortOutcomeGateChecksVerif.ScoreShape
gpt-5.6-luna none blind 2/7 100.0% 0
gpt-5.6-luna low blind 2/7 100.0% 0
gpt-5.6-luna max failed 6/7 87.6% 0
kimi-k3 max failed 6/7 68.1% 0
gpt-5.6-sol xhigh failed 5/7 57.5% 0
gpt-5.6-luna medium failed 5/7 29.2% 0
gpt-5.6-luna xhigh failed 6/7 29.2% 0
gpt-5.6-sol low failed 6/7 26.5% 0
gpt-5.6-sol high failed 5/7 24.8% 0
gpt-5.6-sol max partial 7/7 20.4% 0
gpt-5.6-luna high failed 6/7 18.6% 0
gpt-5.6-sol none failed 6/7 16.8% 0
gpt-5.6-sol medium failed 5/7 12.4% 0
qwen3.8-max max failed 2/7 11.5% 0
claude-opus-5 low partial 7/7 7.1% 0
claude-opus-5 medium partial 7/7 7.1% 0
claude-opus-5 high partial 7/7 7.1% 0
claude-opus-5 xhigh partial 7/7 7.1% 0
claude-opus-5 max partial 7/7 7.1% 0
claude-sonnet-5 low failed 2/7 7.1% 0
claude-sonnet-5 medium partial 7/7 7.1% 0
claude-sonnet-5 high partial 7/7 7.1% 0
claude-sonnet-5 xhigh failed 2/7 7.1% 0
claude-sonnet-5 max failed 6/7 7.1% 0
dsv4-flash max failed 6/7 7.1% 0
glm-5.2 max partial 7/7 7.1% 0