Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

KernelBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
CUDA Kernel GenerationKernelBench Level 3
Executions Count24
31
CUDA Kernel GenerationKernelBench Level 2
Execution Count48
31
CUDA Kernel GenerationKernelBench Level 1
Exec Count46
31
Kernel OptimizationKernelBench 1.0 (test)
Latency (us)0.0063
27
GPU kernel code generation and optimizationKernelBench Level 3 (test)
Correctness Score100
18
GPU kernel code generation and optimizationKernelBench Level 2 (test)
Correctness19
18
GPU kernel code generation and optimizationKernelBench Level 1 (test)
Correctness19
18
Triton kernel generationKernelBench LEVEL3 1.0
Fast1 Score29.8
17
Triton kernel generationKernelBench LEVEL2 1.0
Fast1 Score80.9
17
Triton kernel generationKernelBench LEVEL1 1.0
Fast139.3
17
Matrix MultiplicationKernelBench FP4 Matmul
Throughput (TF/s)2,898
14
Kernel GenerationKernelBench
Speedup3.45
14
Kernel GenerationKernelBench Overall
CR (Round 1)25
10
Kernel GenerationKernelBench Level 2
CR (Round 1)16
10
Kernel GenerationKernelBench Level 1
Correctness Rate (Round 1)34
10
Kernel GenerationKernelBench AVG Level-1 2 3
Correlation Coefficient99.33
8
Kernel GenerationKernelBench Level 3 (Hard)
Correctness (Corr)98
8
Kernel GenerationKernelBench Level 2 (Medium)
Correlation Coefficient100
8
Kernel GenerationKernelBench Level 1 (Easy)
Accuracy100
8
GPU Kernel OptimizationKernelBench Level 3
Fast187
7
GPU Kernel OptimizationKernelBench Level 2
Performance Score 11
7
GPU Kernel OptimizationKernelBench Level 1
Fast1 Performance Score0.71
7
Triton Kernel GenerationKernelBench Level 3
Accuracy76
6
Triton Kernel GenerationKernelBench Level 2
Accuracy96
6
Triton Kernel GenerationKernelBench Level 1
Accuracy69
6
Showing 25 of 32 rows