Navers lab
← All tasks
fw05 Framework rewrite Task 12 / 20

actix-web → axum

miniserve actix-web 4 axum 0.7 (tower)

The language stays, the framework it is organized around is replaced. 3,484 lines, 8 hours per model, and 12,466 checks across 14 modules.

Runs
26

one per configuration

Past rung 1
22

of 26 — the migration happened

Past rung 2
1

of those 22 — every check perfect

Past rung 3
0

of the 1 — accepted

Best composite
60

highest score on this task

The instrument

Acceptance gates

6

decide whether the migration happened

Behavioral modules

14

ported suites, run against the new tree

Frozen checks

12,466

all must pass to open rung three

Verifiers

6

hostile programs, written against the spec

Where the 26 runs stopped

3
Never migrated
21
Migrated, behavior lost
1
Perfect suite, gate rejected
1
Verifier found a difference
0
Accepted

2 runs were perfect on all 12,466 checks; 1 was rejected anyway — the migration had not happened. Of the 1 that reached rung three, 0 survived all six verifiers.

By model

Model Runs Gate Ceil. Where they stopped Mean Best
claude-opus-5 5 5 1
12.0 60
claude-sonnet-5 5 3 0
0.0
dsv4-flash 1 1 0
0.0
glm-5.2 1 1 0
0.0
gpt-5.6-luna 6 6 0
0.0
gpt-5.6-sol 6 5 0
0.0
kimi-k3 1 1 0
0.0
qwen3.8-max 1 0 1
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
claude-opus-5 max broken 6/6 100.0% 2/6 60
qwen3.8-max max blind 2/6 100.0% 0
claude-opus-5 xhigh partial 6/6 99.9% 0
kimi-k3 max partial 6/6 99.9% 0
gpt-5.6-sol max partial 6/6 99.8% 0
claude-opus-5 medium partial 6/6 99.6% 0
claude-opus-5 high partial 6/6 99.6% 0
claude-opus-5 low partial 6/6 99.5% 0
claude-sonnet-5 max partial 6/6 99.1% 0
dsv4-flash max partial 6/6 99.1% 0
gpt-5.6-luna max partial 6/6 99.0% 0
gpt-5.6-sol high partial 6/6 98.7% 0
gpt-5.6-sol xhigh partial 6/6 98.5% 0
claude-sonnet-5 low partial 6/6 98.4% 0
gpt-5.6-luna xhigh partial 6/6 98.3% 0
glm-5.2 max partial 6/6 98.3% 0
claude-sonnet-5 medium partial 6/6 97.8% 0
gpt-5.6-sol medium partial 6/6 97.0% 0
gpt-5.6-sol none partial 6/6 95.9% 0
gpt-5.6-luna medium partial 6/6 95.6% 0
gpt-5.6-luna high partial 6/6 95.1% 0
gpt-5.6-luna none partial 6/6 90.1% 0
gpt-5.6-luna low partial 6/6 75.1% 0
gpt-5.6-sol low failed 5/6 9.9% 0
claude-sonnet-5 high failed 2/6 0.0% 0
claude-sonnet-5 xhigh failed 2/6 0.0% 0