Entry #78
Completed- Hotkey
- 5DVBep…y4CA19
- Sent
- 12 Nov 2026, 02:06 UTC
- Source
- b171739888de
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 | 19.844×Generated 21.915×, real models 17.969× | Above the barGain lower bound -2025.5%Guard passed |
| MLPvs #44 | Done2 of 2 runs | 1.141×Generated 1.017×, real models 1.279× | Above the barGain lower bound -40.5%Guard passed |
| ResNetvs #51 | Done2 of 2 runs | 102.946×Generated 114.098×, real models 92.883× | Above the barGain lower bound -11108.7%Guard passed |
| MobileNetvs #53 | Done2 of 2 runs | 95.982×Generated 112.080×, real models 82.196× | Above the barGain lower bound -11894.1%Guard passed |
| Normalized MLPvs #48 | Done2 of 2 runs | 57.529×Generated 89.892×, real models 36.817× | Above the barGain lower bound -6913.5%Guard passed |
| Mixervs #47 | Done2 of 2 runs | 164.103×Generated 176.953×, real models 152.185× | Above the barGain lower bound -17689.5%Guard passed |
| Recurrentvs #54 | Done2 of 2 runs | 0.997×Generated 0.975×, real models 1.019× | Above the barGain lower bound -2.4%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 21.915× · real models 17.969×
MachineTime
- prod-amd64Seed 80425665119.999×Done1 attempt0.207× of the baseline kernels' time
- prod-arm64Seed 80425665119.690×Done1 attempt0.233× of the baseline kernels' time
By model and inputGuard at 1.100×
MLP
- Batch 1, normal0.987×
- Batch 1, sparse1.199×
- Batch 1, wide0.903×
Mixer
- Batch 1, normal157.772×
- Batch 1, sparse164.502×
- Batch 1, wide188.050×
ResNet
- Batch 1, normal109.629×
- Batch 1, sparse126.641×
- Batch 1, wide111.408×
MobileNet
- Batch 1, normal91.995×
- Batch 1, sparse96.265×
- Batch 1, wide93.494×
Recurrent
- Batch 1, normal0.936×
- Batch 1, sparse0.915×
- Batch 1, wide0.903×
Normalized MLP
- Batch 1, normal72.136×
- Batch 1, sparse69.713×
- Batch 1, wide76.840×
Real models
- appliance-energy-mixer on Appliance Energy Prediction205.633×
- compact-mixer on digits205.590×
- compact-mixer on fashion154.553×
- compact-mixer on mnist154.876×
- compact-mlp on digits0.791×
- compact-mlp on fashion0.815×
- compact-mlp on mnist1.002×
- compact-mobilenet on digits60.614×
- compact-mobilenet on fashion84.458×
- compact-mobilenet on mnist78.560×
- compact-normalized_mlp on digits72.536×
- compact-normalized_mlp on fashion25.675×
- compact-normalized_mlp on mnist25.596×
- compact-resnet on digits73.634×
- compact-resnet on fashion122.909×
- compact-resnet on mnist117.779×
- appliance-gru on appliance-energy0.953×
- mitbih-gru on mitbih0.986×
- mnist-rows-lstm on mnist-rows0.806×
- speech-commands-gru on speech-commands0.995×
- speech-commands-lstm-gru on speech-commands0.913×
- spoken-arabic-digit-lstm on spoken-arabic-digit0.935×
- tiny-shakespeare-lstm on tiny-shakespeare0.851×
- uci-har-gru on uci-har1.056×
- uci-har-lstm on uci-har0.952×
- uci-har-mixer on UCI-HAR166.571×
- uci-har-mlp on UCI-HAR1.022×
- uci-har-mobilenet on UCI-HAR76.597×
- uci-har-normalized_mlp on UCI-HAR20.669×
- uci-har-resnet on UCI-HAR81.823×
MLP2 runs
RunsGenerated 1.017× · real models 1.279×
MachineTime
- prod-amd64Seed 8042566511.250×Done1 attempt0.017× of the baseline kernels' time
- prod-arm64Seed 8042566511.041×Done1 attempt0.017× of the baseline kernels' time
By model and inputGuard at 1.100×
MLP
- Batch 1, normal0.955×
- Batch 1, sparse0.970×
- Batch 1, wide0.993×
Real models
- compact-mlp on digits1.135×
- compact-mlp on fashion0.796×
- compact-mlp on mnist2.993×
- uci-har-mlp on UCI-HAR0.990×
ResNet2 runs
RunsGenerated 114.098× · real models 92.883×
MachineTime
- prod-amd64Seed 804256651106.026×Done1 attempt0.996× of the baseline kernels' time
- prod-arm64Seed 80425665199.954×Done1 attempt0.997× of the baseline kernels' time
By model and inputGuard at 1.100×
ResNet
- Batch 1, normal111.598×
- Batch 1, sparse128.696×
- Batch 1, wide111.631×
Real models
- compact-resnet on digits65.737×
- compact-resnet on fashion121.199×
- compact-resnet on mnist117.375×
- uci-har-resnet on UCI-HAR79.591×
MobileNet2 runs
RunsGenerated 112.080× · real models 82.196×
MachineTime
- prod-amd64Seed 80425665190.283×Done1 attempt1.189× of the baseline kernels' time
- prod-arm64Seed 804256651102.041×Done1 attempt1.159× of the baseline kernels' time
By model and inputGuard at 1.100×
MobileNet
- Batch 1, normal128.424×
- Batch 1, sparse95.042×
- Batch 1, wide96.445×
Real models
- compact-mobilenet on digits66.468×
- compact-mobilenet on fashion95.353×
- compact-mobilenet on mnist93.433×
- uci-har-mobilenet on UCI-HAR77.083×
Normalized MLP2 runs
RunsGenerated 89.892× · real models 36.817×
MachineTime
- prod-amd64Seed 80425665166.649×Done1 attempt0.625× of the baseline kernels' time
- prod-arm64Seed 80425665149.657×Done1 attempt0.637× of the baseline kernels' time
By model and inputGuard at 1.100×
Normalized MLP
- Batch 1, normal87.736×
- Batch 1, sparse86.333×
- Batch 1, wide90.963×
Real models
- compact-normalized_mlp on digits84.858×
- compact-normalized_mlp on fashion30.989×
- compact-normalized_mlp on mnist36.713×
- uci-har-normalized_mlp on UCI-HAR19.031×
Mixer2 runs
RunsGenerated 176.953× · real models 152.185×
MachineTime
- prod-amd64Seed 804256651163.344×Done1 attempt0.842× of the baseline kernels' time
- prod-arm64Seed 804256651164.864×Done1 attempt0.847× of the baseline kernels' time
By model and inputGuard at 1.100×
Mixer
- Batch 1, normal173.818×
- Batch 1, sparse180.908×
- Batch 1, wide205.479×
Real models
- appliance-energy-mixer on Appliance Energy Prediction217.742×
- compact-mixer on digits105.636×
- compact-mixer on fashion161.606×
- compact-mixer on mnist156.958×
- uci-har-mixer on UCI-HAR139.916×
Recurrent2 runs
RunsGenerated 0.975× · real models 1.019×
MachineTime
- prod-amd64Seed 8042566511.024×Done1 attempt0.011× of the baseline kernels' time
- prod-arm64Seed 8042566510.971×Done1 attempt0.012× of the baseline kernels' time
By model and inputGuard at 1.100×
Recurrent
- Batch 1, normal0.994×
- Batch 1, sparse0.993×
- Batch 1, wide0.939×
Real models
- appliance-gru on appliance-energy0.916×
- mitbih-gru on mitbih0.971×
- mnist-rows-lstm on mnist-rows1.168×
- speech-commands-gru on speech-commands0.952×
- speech-commands-lstm-gru on speech-commands0.973×
- spoken-arabic-digit-lstm on spoken-arabic-digit1.034×
- tiny-shakespeare-lstm on tiny-shakespeare1.177×
- uci-har-gru on uci-har0.964×
- uci-har-lstm on uci-har1.054×