OpenAnvil
Build and grade React Native apps · Every run is data · Demo week of Aug 11
6 runs · 1 live
Average reward
0.00
/ 1.0
Weighted build 0.2 + functional 0.3 + flow 0.35 + contract 0.15
Runs today
0
6 total in corpus
Running
1
Live updates
Success rate
33%
2 succeeded
Top model
claude / spark-v2
0.71 mean · 12 runs · warm palette
SparkBedrockMock
Recent runs
View all →| Run ID | Trial | Platform | Model | Reward | Status | Duration |
|---|---|---|---|---|---|---|
| calculator_ios_20260 | calculator | ios | unknown/6p9fm7 | - | failed | - |
| calculator_ios_20260 | calculator | ios | mock/deepseek.v3.2 | - | failed | - |
| calculator_ios_20260 | calculator | ios | mock/deepseek.v3.2 | - | provisioning | - |
| calculator_ios_20260 | calculator | ios | mock/deepseek.v3.2 | - | running | - |
| calculator_ios_17852 | calculator | ios | unknown/unknown | - | succeeded | - |
| calculator_ios_17852 | calculator | ios | unknown/unknown | - | succeeded | - |
Duration trend
iOS vs Android
Runs by trial
calculator
3
music player
1
travel site
2
Tier breakdown
build
functional
flow
contract