Merge generated-exercism-polyglot (main and #9) into generated-swebench

29002f7

Select commit

Loading

Failed to load commit list.

Uh oh!

There was an error while loading. Please reload this page.

Sign in for the full log view

Sample tasks on: pull_request

Choose a sample of each built-locally dataset

swebench-lite@1.0 mwaskom__seaborn-3407

swebench-lite@1.0 pydata__xarray-4248

swebench-lite@1.0 django__django-14915

swebench-lite@1.0 sympy__sympy-20154

swebench-lite@1.0 sphinx-doc__sphinx-8627

swebench-lite@1.0 scikit-learn__scikit-learn-14983

swebench-lite@1.0 pytest-dev__pytest-7220

swebench-lite@1.0 astropy__astropy-14182

swebench-lite@1.0 pallets__flask-5063

swebench-lite@1.0 psf__requests-3362

swebench-verified@1.0 django__django-13363

swebench-verified@1.0 sphinx-doc__sphinx-11510

swebench-verified@1.0 sympy__sympy-14711

swebench-verified@1.0 scikit-learn__scikit-learn-15100

swebench-verified@1.0 astropy__astropy-7606

swebench-verified@1.0 pydata__xarray-4075

swebench-verified@1.0 pytest-dev__pytest-7236

swebench-verified@1.0 psf__requests-2317

swebench-verified@1.0 mwaskom__seaborn-3069

swebench-verified@1.0 pallets__flask-5014

Summarise the sample

Exercism polyglot on: pull_request 1

cpp: build the image, then every oracle must pass and every stub fail

go: build the image, then every oracle must pass and every stub fail

java: build the image, then every oracle must pass and every stub fail

javascript: build the image, then every oracle must pass and every stub fail

python: build the image, then every oracle must pass and every stub fail

rust: build the image, then every oracle must pass and every stub fail

Validate on: pull_request 2

Descriptors and scripts

Fetch each source at its pinned commit

Generate each generated dataset twice and check every task

BigCodeBench on: pull_request 1

Generate the tasks and split them between runners

Pull or build the image

Check shard 1 of 2

Check shard 2 of 2

Summarise the checks

Choose a sample of each built-locally dataset

succeeded Oct 22, 2026 in 26s

Loading

Re-running jobs...