Entry #76
Completed- Hotkey
- 5FPBwB…mEXicA
- Sent
- 12 Nov 2026, 01:27 UTC
- Source
- b4525874ae04
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 #50 | Done2 of 2 runs | 15.691×Generated 16.992×, real models 14.489× | Above the barGain lower bound -1633.2%Guard passed |
| MLPvs #44 | Done2 of 2 runs | 1.063×Generated 0.927×, real models 1.218× | Above the barGain lower bound -31.5%Guard passed |
| ResNetvs #51 | Done2 of 2 runs | 4.476×Generated 5.179×, real models 3.868× | Above the barGain lower bound -451.4%Guard passed |
| MobileNetvs #53 | Done2 of 2 runs | 1.020×Generated 1.011×, real models 1.028× | Above the barGain lower bound -13.5%Guard passed |
| Normalized MLPvs #48 | Done2 of 2 runs | 37.289×Generated 44.382×, real models 31.330× | Above the barGain lower bound -4515.9%Guard passed |
| Mixervs #47 | Done2 of 2 runs | 174.302×Generated 190.700×, real models 159.314× | Above the barGain lower bound -19277.2%Guard passed |
| Recurrentvs #54 | Done2 of 2 runs | 825.347×Generated 711.150×, real models 957.882× | Above the barGain lower bound -86727.0%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 16.992× · real models 14.489×
MachineTime
- prod-amd64Seed 11395725717.226×Done1 attempt0.162× of the baseline kernels' time
- prod-arm64Seed 11395725714.292×Done1 attempt0.172× of the baseline kernels' time
By model and inputGuard at 1.100×
MLP
- Batch 1, normal1.023×
- Batch 1, sparse1.082×
- Batch 1, wide1.080×
Mixer
- Batch 1, normal204.372×
- Batch 1, sparse190.066×
- Batch 1, wide213.195×
ResNet
- Batch 1, normal3.817×
- Batch 1, sparse4.193×
- Batch 1, wide3.757×
MobileNet
- Batch 1, normal0.984×
- Batch 1, sparse0.983×
- Batch 1, wide1.016×
Recurrent
- Batch 1, normal715.554×
- Batch 1, sparse642.059×
- Batch 1, wide668.465×
Normalized MLP
- Batch 1, normal57.242×
- Batch 1, sparse56.694×
- Batch 1, wide58.329×
Real models
- appliance-energy-mixer on Appliance Energy Prediction221.418×
- compact-mixer on digits195.524×
- compact-mixer on fashion163.131×
- compact-mixer on mnist153.817×
- compact-mlp on digits0.660×
- compact-mlp on fashion0.964×
- compact-mlp on mnist1.021×
- compact-mobilenet on digits0.097×
- compact-mobilenet on fashion0.893×
- compact-mobilenet on mnist0.857×
- compact-normalized_mlp on digits67.526×
- compact-normalized_mlp on fashion34.353×
- compact-normalized_mlp on mnist33.214×
- compact-resnet on digits2.498×
- compact-resnet on fashion3.808×
- compact-resnet on mnist3.874×
- appliance-gru on appliance-energy697.824×
- mitbih-gru on mitbih908.833×
- mnist-rows-lstm on mnist-rows723.100×
- speech-commands-gru on speech-commands713.074×
- speech-commands-lstm-gru on speech-commands860.007×
- spoken-arabic-digit-lstm on spoken-arabic-digit1142.744×
- tiny-shakespeare-lstm on tiny-shakespeare819.268×
- uci-har-gru on uci-har840.365×
- uci-har-lstm on uci-har1144.983×
- uci-har-mixer on UCI-HAR167.944×
- uci-har-mlp on UCI-HAR0.941×
- uci-har-mobilenet on UCI-HAR0.945×
- uci-har-normalized_mlp on UCI-HAR20.222×
- uci-har-resnet on UCI-HAR5.363×
MLP2 runs
RunsGenerated 0.927× · real models 1.218×
MachineTime
- prod-amd64Seed 1139572570.973×Done1 attempt0.014× of the baseline kernels' time
- prod-arm64Seed 1139572571.161×Done1 attempt0.013× of the baseline kernels' time
By model and inputGuard at 1.100×
MLP
- Batch 1, normal0.974×
- Batch 1, sparse0.916×
- Batch 1, wide0.927×
Real models
- compact-mlp on digits0.813×
- compact-mlp on fashion1.572×
- compact-mlp on mnist1.895×
- uci-har-mlp on UCI-HAR0.910×
ResNet2 runs
RunsGenerated 5.179× · real models 3.868×
MachineTime
- prod-amd64Seed 1139572574.058×Done1 attempt0.030× of the baseline kernels' time
- prod-arm64Seed 1139572574.937×Done1 attempt0.034× of the baseline kernels' time
By model and inputGuard at 1.100×
ResNet
- Batch 1, normal5.322×
- Batch 1, sparse4.314×
- Batch 1, wide5.150×
Real models
- compact-resnet on digits2.853×
- compact-resnet on fashion3.928×
- compact-resnet on mnist3.817×
- uci-har-resnet on UCI-HAR5.235×
MobileNet2 runs
RunsGenerated 1.011× · real models 1.028×
MachineTime
- prod-amd64Seed 1139572571.025×Done1 attempt0.012× of the baseline kernels' time
- prod-arm64Seed 1139572571.015×Done1 attempt0.010× of the baseline kernels' time
By model and inputGuard at 1.100×
MobileNet
- Batch 1, normal0.998×
- Batch 1, sparse1.018×
- Batch 1, wide1.008×
Real models
- compact-mobilenet on digits1.064×
- compact-mobilenet on fashion1.017×
- compact-mobilenet on mnist1.031×
- uci-har-mobilenet on UCI-HAR1.002×
Normalized MLP2 runs
RunsGenerated 44.382× · real models 31.330×
MachineTime
- prod-amd64Seed 11395725739.725×Done1 attempt0.472× of the baseline kernels' time
- prod-arm64Seed 11395725735.002×Done1 attempt0.481× of the baseline kernels' time
By model and inputGuard at 1.100×
Normalized MLP
- Batch 1, normal44.128×
- Batch 1, sparse50.633×
- Batch 1, wide46.666×
Real models
- compact-normalized_mlp on digits62.393×
- compact-normalized_mlp on fashion25.181×
- compact-normalized_mlp on mnist25.030×
- uci-har-normalized_mlp on UCI-HAR24.500×
Mixer2 runs
RunsGenerated 190.700× · real models 159.314×
MachineTime
- prod-amd64Seed 113957257188.127×Done1 attempt0.864× of the baseline kernels' time
- prod-arm64Seed 113957257161.492×Done1 attempt0.872× of the baseline kernels' time
By model and inputGuard at 1.100×
Mixer
- Batch 1, normal180.140×
- Batch 1, sparse189.020×
- Batch 1, wide223.554×
Real models
- appliance-energy-mixer on Appliance Energy Prediction253.346×
- compact-mixer on digits116.529×
- compact-mixer on fashion159.248×
- compact-mixer on mnist155.719×
- uci-har-mixer on UCI-HAR140.187×
Recurrent2 runs
RunsGenerated 711.150× · real models 957.882×
MachineTime
- prod-amd64Seed 113957257881.204×Done1 attempt8.075× of the baseline kernels' time
- prod-arm64Seed 113957257773.031×Done1 attempt8.422× of the baseline kernels' time
By model and inputGuard at 1.100×
Recurrent
- Batch 1, normal733.357×
- Batch 1, sparse714.937×
- Batch 1, wide691.169×
Real models
- appliance-gru on appliance-energy752.548×
- mitbih-gru on mitbih924.863×
- mnist-rows-lstm on mnist-rows1009.970×
- speech-commands-gru on speech-commands678.809×
- speech-commands-lstm-gru on speech-commands874.437×
- spoken-arabic-digit-lstm on spoken-arabic-digit1291.351×
- tiny-shakespeare-lstm on tiny-shakespeare1209.324×
- uci-har-gru on uci-har819.073×
- uci-har-lstm on uci-har1272.050×