sklbench builds comparison dashboard

Hardware

CPU

Intel(R) Xeon(R) 6787P

X86_64, 172 physical cores, 344 logical CPUs

499 GB RAM

GPU(s)

No GPU detected.

sklearn

Python 3.12.13

Packages

scikit-learn 1.9.0 (pypi)
numpy 2.4.6 (conda-forge)
scipy 1.17.1 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (128 threads)
libgomp (344 threads)

OpenMP

GNU libgomp (OpenMP 4.5)
GOMP_SPINCOUNT: 300000

Full environment

view pixi env JSON

sklearn-conda

Python 3.12.13

Packages

scikit-learn 1.9.0 (conda-forge)
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (128 threads)
libgomp (344 threads)

OpenMP

GNU libgomp (OpenMP 4.5)
GOMP_SPINCOUNT: 300000

Full environment

view pixi env JSON

sklearn-dev-libomp@cakedev0:hgb/adapt_to_active_wait

Python 3.12.13

Packages

scikit-learn @ 27d3e13ba
numpy 2.5.2 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.34 (128 threads)
libomp (344 threads)

OpenMP

Intel/LLVM OpenMP (spec 201611)
KMP_BLOCKTIME: 200ms

Full environment

view pixi env JSON

sklearn-dev-libomp@cakedev0:main

Python 3.12.13

Packages

scikit-learn @ 6aa2f57c2
numpy 2.5.2 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.34 (128 threads)
libomp (344 threads)

OpenMP

Intel/LLVM OpenMP (spec 201611)
KMP_BLOCKTIME: 200ms

Full environment

view pixi env JSON

sklearn-dev@cakedev0:hgb/adapt_to_active_wait

Python 3.12.13

Packages

scikit-learn @ 27d3e13ba
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (128 threads)
libgomp (344 threads)

OpenMP

GNU libgomp (OpenMP 4.5)
GOMP_SPINCOUNT: 300000

Full environment

view pixi env JSON

sklearn-dev@cakedev0:hgb/both_threads_optim

Python 3.12.13

Packages

scikit-learn @ 44f1cbbde
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (128 threads)
libgomp (344 threads)

OpenMP

GNU libgomp (OpenMP 4.5)
GOMP_SPINCOUNT: 300000

Full environment

view pixi env JSON

sklearn-dev@cakedev0:main

Python 3.12.13

Packages

scikit-learn @ 6aa2f57c2
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (128 threads)
libgomp (344 threads)

OpenMP

GNU libgomp (OpenMP 4.5)
GOMP_SPINCOUNT: 300000

Full environment

view pixi env JSON

sklearn-mkl

Python 3.12.13

Packages

scikit-learn 1.9.0 (conda-forge)
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libmkl_rt 2026.0-Product (172 threads)
libomp (344 threads)

Full environment

view pixi env JSON

sklearn-openblas-openmp

Python 3.12.13

Packages

scikit-learn 1.9.0 (conda-forge)
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (128 threads)
libomp (344 threads)

OpenMP

Intel/LLVM OpenMP (spec 201611)
KMP_BLOCKTIME: 200ms

Full environment

view pixi env JSON

sklearn-openblas-pthreads

Python 3.12.13

Packages

scikit-learn 1.9.0 (conda-forge)
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (128 threads)
libgomp (344 threads)

OpenMP

GNU libgomp (OpenMP 4.5)
GOMP_SPINCOUNT: 300000

Full environment

view pixi env JSON

linear / fit (182 points)

● Metrics and benchmark setup match the baseline

■ Metrics match the baseline, but some comparison details are worth reporting:

🔁 Number of iteration differs: this might mean algorithms differ - LogisticRegression (2)

linear / predict (182 points)

● Metrics and benchmark setup match the baseline

■ Metrics match the baseline, but some comparison details are worth reporting:

🔁 Number of iteration differs: this might mean algorithms differ - LogisticRegression (2)

Detailed results

tree-based / fit (164 points)

● Metrics and benchmark setup match the baseline

tree-based / predict (164 points)

● Metrics and benchmark setup match the baseline

Detailed results

clustering / fit (27 points)

● Metrics and benchmark setup match the baseline

■ Metrics match the baseline, but some comparison details are worth reporting:

🔁 Number of iteration differs: this might mean algorithms differ - KMeans (1)

✕ Benchmark run failed, shown at the bottom of its column (7 points)

clustering / predict (27 points)

● Metrics and benchmark setup match the baseline

■ Metrics match the baseline, but some comparison details are worth reporting:

🔁 Number of iteration differs: this might mean algorithms differ - KMeans (1)

✕ Benchmark run failed, shown at the bottom of its column (7 points)

Detailed results

Hardware

CPU

Intel(R) Core(TM) Ultra X7 358H

X86_64, 16 physical cores, 16 logical CPUs

31 GB RAM

GPU(s)

level_zero:gpu:0: Intel(R) Arc(TM) B390 GPU (29 GB)

sklearn

Python 3.12.13

Packages

scikit-learn 1.9.0 (pypi)
numpy 2.4.6 (conda-forge)
scipy 1.17.1 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (16 threads)
libgomp (16 threads)

OpenMP

GNU libgomp (OpenMP 4.5)
GOMP_SPINCOUNT: 300000

Full environment

view pixi env JSON

sklearn-cf-mkl

Python 3.12.13

Packages

scikit-learn 1.9.0 (conda-forge)
numpy 2.5.2 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libmkl_rt 2026.1-Product (16 threads)
libomp (16 threads)

OpenMP

Intel/LLVM OpenMP (spec 201611)
KMP_BLOCKTIME: 0ms

Full environment

view pixi env JSON

sklearn-conda

Python 3.12.13

Packages

scikit-learn 1.9.0 (conda-forge)
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (16 threads)
libgomp (16 threads)

OpenMP

GNU libgomp (OpenMP 4.5)
GOMP_SPINCOUNT: 1

Full environment

view pixi env JSON

sklearn-dev-libomp@cakedev0:hgb/adapt_to_active_wait

Python 3.12.13

Packages

scikit-learn @ 27d3e13ba
numpy 2.5.2 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.34 (16 threads)
libomp (16 threads)

OpenMP

Intel/LLVM OpenMP (spec 201611)
KMP_BLOCKTIME: 0ms

Full environment

view pixi env JSON

sklearn-dev-libomp@cakedev0:main

Python 3.12.13

Packages

scikit-learn @ 6aa2f57c2
numpy 2.5.2 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.34 (16 threads)
libomp (16 threads)

OpenMP

Intel/LLVM OpenMP (spec 201611)
KMP_BLOCKTIME: 0ms

Full environment

view pixi env JSON

sklearn-dev@cakedev0:hgb/adapt_to_active_wait

Python 3.12.13

Packages

scikit-learn @ 27d3e13ba
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (16 threads)
libgomp (16 threads)

OpenMP

GNU libgomp (OpenMP 4.5)
GOMP_SPINCOUNT: 1

Full environment

view pixi env JSON

sklearn-dev@cakedev0:main

Python 3.12.13

Packages

scikit-learn @ e27ccf585
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (16 threads)
libgomp (16 threads)

OpenMP

GNU libgomp (OpenMP 4.5)
GOMP_SPINCOUNT: 1

Full environment

view pixi env JSON

sklearn-mkl

Python 3.12.13

Packages

scikit-learn 1.9.0 (conda-forge)
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libmkl_rt 2026.0-Product (16 threads)
libomp (16 threads)

Full environment

view pixi env JSON

sklearn-openblas-openmp

Python 3.12.13

Packages

scikit-learn 1.9.0 (conda-forge)
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (16 threads)
libomp (16 threads)

OpenMP

Intel/LLVM OpenMP (spec 201611)
KMP_BLOCKTIME: 0ms

Full environment

view pixi env JSON

sklearn-openblas-pthreads

Python 3.12.13

Packages

scikit-learn 1.9.0 (conda-forge)
numpy 2.5.0 (conda-forge)
scipy 1.18.0 (conda-forge)
pandas 2.3.3 (conda-forge)

Threadpools

libopenblas 0.3.33 (16 threads)
libgomp (16 threads)

OpenMP

GNU libgomp (OpenMP 4.5)
GOMP_SPINCOUNT: 1

Full environment

view pixi env JSON

linear / fit (229 points)

● Metrics and benchmark setup match the baseline

■ Metrics match the baseline, but some comparison details are worth reporting:

🔁 Number of iteration differs: this might mean algorithms differ - LogisticRegression (2)

linear / predict (229 points)

● Metrics and benchmark setup match the baseline

■ Metrics match the baseline, but some comparison details are worth reporting:

🔁 Number of iteration differs: this might mean algorithms differ - LogisticRegression (2)

Detailed results

tree-based / fit (498 points)

● Metrics and benchmark setup match the baseline

tree-based / predict (498 points)

● Metrics and benchmark setup match the baseline

Detailed results

clustering / fit (44 points)

● Metrics and benchmark setup match the baseline

■ Metrics match the baseline, but some comparison details are worth reporting:

🔁 Number of iteration differs: this might mean algorithms differ - KMeans (5)

clustering / predict (44 points)

● Metrics and benchmark setup match the baseline

■ Metrics match the baseline, but some comparison details are worth reporting:

🔁 Number of iteration differs: this might mean algorithms differ - KMeans (5)

Detailed results