Entry #22
Completed- Hotkey
- 5F9Hgs…hLNbXt
- Sent
- 11 Nov 2026, 00:53 UTC
- Source
- ec13e87b0cf4
Progress
- Queued
- Proof
- Planned
- Timing
- Done
Done means every board has a decision. It does not mean the entry took a board over.
On each board
| Board | Runs | Time | Decision |
|---|---|---|---|
| Overallvs #29 | Done2 of 2 runs | 44.167×Generated 49.971×, real models 39.037× | Above the barGain lower bound -4600.7%Guard passed |
| MLPvs #1 | Done2 of 2 runs | 0.956×Generated 0.965×, real models 0.947× | Not significantGain lower bound -11.2%Guard passed |
| ResNetvs #27 | Done2 of 2 runs | 76.217×Generated 108.906×, real models 53.339× | Above the barGain lower bound -7980.3%Guard passed |
| MobileNetvs #28 | Done2 of 2 runs | 55.477×Generated 86.038×, real models 35.771× | Above the barGain lower bound -5776.7%Guard passed |
| Normalized MLPvs #6 | Done2 of 2 runs | 41.842×Generated 50.175×, real models 34.892× | Above the barGain lower bound -5114.4%Guard passed |
| Mixervs #24 | Done2 of 2 runs | 160.490×Generated 166.773×, real models 154.443× | Above the barGain lower bound -18082.3%Guard passed |
| Recurrentvs #25 | Done2 of 2 runs | 215.613×Generated 193.685×, real models 240.023× | Above the barGain lower bound -22932.9%Guard passed |
The source stays private while it holds a board, and for entries that never held one.
Every run
Each board times the entry on every benchmark machine, over fresh seeds, on generated workloads and on trained models with real data. A run's time combines the two suites by their published weights; the bars below split it by model, batch and input, and by real model.
Overall2 runs
RunsGenerated 49.971× · real models 39.037×
MachineTime
- prod-amd64Seed 86441669346.011×Done1 attempt0.625× of the baseline kernels' time
- prod-arm64Seed 86441669342.397×Done1 attempt0.650× of the baseline kernels' time
By model and inputGuard at 1.100×
MLP
- Batch 1, normal0.978×
- Batch 1, sparse1.031×
- Batch 1, wide1.129×
Mixer
- Batch 1, normal167.910×
- Batch 1, sparse157.784×
- Batch 1, wide188.866×
ResNet
- Batch 1, normal100.971×
- Batch 1, sparse117.980×
- Batch 1, wide101.831×
MobileNet
- Batch 1, normal82.868×
- Batch 1, sparse87.244×
- Batch 1, wide83.604×
Recurrent
- Batch 1, normal193.032×
- Batch 1, sparse191.665×
- Batch 1, wide189.220×
Normalized MLP
- Batch 1, normal47.164×
- Batch 1, sparse49.113×
- Batch 1, wide49.425×
Real models
- appliance-energy-mixer on Appliance Energy Prediction235.728×
- compact-mixer on digits160.262×
- compact-mixer on fashion139.446×
- compact-mixer on mnist139.800×
- compact-mlp on digits0.893×
- compact-mlp on fashion1.381×
- compact-mlp on mnist1.679×
- compact-mobilenet on digits50.316×
- compact-mobilenet on fashion66.247×
- compact-mobilenet on mnist48.499×
- compact-normalized_mlp on digits91.256×
- compact-normalized_mlp on fashion24.531×
- compact-normalized_mlp on mnist25.893×
- compact-resnet on digits56.360×
- compact-resnet on fashion93.514×
- compact-resnet on mnist76.290×
- appliance-gru on appliance-energy188.594×
- mitbih-gru on mitbih228.885×
- mnist-rows-lstm on mnist-rows318.275×
- speech-commands-gru on speech-commands117.926×
- speech-commands-lstm-gru on speech-commands223.837×
- spoken-arabic-digit-lstm on spoken-arabic-digit393.945×
- tiny-shakespeare-lstm on tiny-shakespeare347.928×
- uci-har-gru on uci-har190.718×
- uci-har-lstm on uci-har286.274×
- uci-har-mixer on UCI-HAR144.695×
- uci-har-mlp on UCI-HAR1.089×
- uci-har-mobilenet on UCI-HAR14.123×
- uci-har-normalized_mlp on UCI-HAR23.444×
- uci-har-resnet on UCI-HAR25.035×
MLP2 runs
RunsGenerated 0.965× · real models 0.947×
MachineTime
- prod-amd64Seed 8644166930.973×Done1 attempt0.023× of the baseline kernels' time
- prod-arm64Seed 8644166930.939×Done1 attempt0.016× of the baseline kernels' time
By model and inputGuard at 1.100×
MLP
- Batch 1, normal0.931×
- Batch 1, sparse1.002×
- Batch 1, wide0.960×
Real models
- compact-mlp on digits0.915×
- compact-mlp on fashion0.967×
- compact-mlp on mnist0.918×
- uci-har-mlp on UCI-HAR0.990×
ResNet2 runs
RunsGenerated 108.906× · real models 53.339×
MachineTime
- prod-amd64Seed 86441669380.735×Done1 attempt0.989× of the baseline kernels' time
- prod-arm64Seed 86441669371.951×Done1 attempt0.999× of the baseline kernels' time
By model and inputGuard at 1.100×
ResNet
- Batch 1, normal102.696×
- Batch 1, sparse116.942×
- Batch 1, wide103.477×
Real models
- compact-resnet on digits52.033×
- compact-resnet on fashion67.122×
- compact-resnet on mnist45.443×
- uci-har-resnet on UCI-HAR51.001×
MobileNet2 runs
RunsGenerated 86.038× · real models 35.771×
MachineTime
- prod-amd64Seed 86441669358.433×Done1 attempt1.209× of the baseline kernels' time
- prod-arm64Seed 86441669352.671×Done1 attempt1.168× of the baseline kernels' time
By model and inputGuard at 1.100×
MobileNet
- Batch 1, normal85.159×
- Batch 1, sparse86.056×
- Batch 1, wide87.537×
Real models
- compact-mobilenet on digits44.563×
- compact-mobilenet on fashion37.388×
- compact-mobilenet on mnist25.851×
- uci-har-mobilenet on UCI-HAR38.014×
Normalized MLP2 runs
RunsGenerated 50.175× · real models 34.892×
MachineTime
- prod-amd64Seed 86441669345.764×Done1 attempt0.486× of the baseline kernels' time
- prod-arm64Seed 86441669338.255×Done1 attempt0.490× of the baseline kernels' time
By model and inputGuard at 1.100×
Normalized MLP
- Batch 1, normal50.119×
- Batch 1, sparse53.329×
- Batch 1, wide50.599×
Real models
- compact-normalized_mlp on digits69.199×
- compact-normalized_mlp on fashion37.291×
- compact-normalized_mlp on mnist31.429×
- uci-har-normalized_mlp on UCI-HAR18.276×
Mixer2 runs
RunsGenerated 166.773× · real models 154.443×
MachineTime
- prod-amd64Seed 864416693170.175×Done1 attempt0.849× of the baseline kernels' time
- prod-arm64Seed 864416693151.356×Done1 attempt0.856× of the baseline kernels' time
By model and inputGuard at 1.100×
Mixer
- Batch 1, normal150.987×
- Batch 1, sparse158.342×
- Batch 1, wide191.257×
Real models
- appliance-energy-mixer on Appliance Energy Prediction217.764×
- compact-mixer on digits142.745×
- compact-mixer on fashion140.203×
- compact-mixer on mnist140.734×
- uci-har-mixer on UCI-HAR143.266×
Recurrent2 runs
RunsGenerated 193.685× · real models 240.023×
MachineTime
- prod-amd64Seed 864416693217.657×Done1 attempt7.891× of the baseline kernels' time
- prod-arm64Seed 864416693213.588×Done1 attempt8.229× of the baseline kernels' time
By model and inputGuard at 1.100×
Recurrent
- Batch 1, normal192.683×
- Batch 1, sparse193.584×
- Batch 1, wide190.264×
Real models
- appliance-gru on appliance-energy185.226×
- mitbih-gru on mitbih228.493×
- mnist-rows-lstm on mnist-rows321.827×
- speech-commands-gru on speech-commands118.582×
- speech-commands-lstm-gru on speech-commands224.543×
- spoken-arabic-digit-lstm on spoken-arabic-digit385.749×
- tiny-shakespeare-lstm on tiny-shakespeare347.765×
- uci-har-gru on uci-har190.337×
- uci-har-lstm on uci-har285.527×