Upload from GitHub Actions: blocklist: drop the grace for slow failing models, not just egregious ones

Upload from GitHub Actions: models: drop kimi-k2.6; exclude egregiously-failing models after one run

Upload from GitHub Actions: eval: check runtime budget per-batch so a slow model can't blow the 6h cap

Upload from GitHub Actions: eval: fix per-combo resilience (tqdm_asyncio.gather has no return_exceptions)

Upload from GitHub Actions: eval: don't let one bad (task,language) combo crash the whole run

Upload from GitHub Actions: models: migrate catalog to /api/v1/models; enforce privacy per-request

Upload from GitHub Actions: discovery: surface newer flagships from curated families; blocklist: require 2 consecutive bad runs

Upload from GitHub Actions: discovery: one flagship per product line; eval: graceful 6h-safe runtime budget

Upload from GitHub Actions: main: gate publishing on coverage-completeness, not just error rate

Upload from GitHub Actions: util: retry HF push with backoff; write local snapshot before push

Upload from GitHub Actions: main: checkpoint per fully-evaluated model instead of once at the end

Upload from GitHub Actions: models: replace claude-opus-4.5/4.6 with 4.8 in curated list

Upload from GitHub Actions: discovery: filter out voice/ASR/vision/build endpoints

Upload from GitHub Actions: backend: handle null creation_date in three apply() calls

Upload from GitHub Actions: fast-fail on account-level API errors; refuse to ship runs with >80% errors

Upload from GitHub Actions: unblock workflow: materialize gcloud creds on runner; lazy-init translate client

Upload from GitHub Actions: guard main.py against partial-scale HF pushes; restore aggregated results

Upload from GitHub Actions: refresh pyproject metadata + README HF frontmatter

Upload from GitHub Actions: new model

Upload from GitHub Actions: added new models

Upload from GitHub Actions: added new models

Upload from GitHub Actions: Merge pull request #28 from datenlabor-bmz/jn-dev

Upload from GitHub Actions: cleaned up code

Upload from GitHub Actions: added opus 4.5

Upload from GitHub Actions: add gpt-5.1, gemini-3

Upload from GitHub Actions: flores filter for available dev split

Upload from GitHub Actions: model name no bracket stuff

Upload from GitHub Actions: drop normalization

Upload from GitHub Actions: improve norwegian fix

Upload from GitHub Actions: fix norwegian

Upload from GitHub Actions: Merge pull request #22 from datenlabor-bmz/dev

Upload from GitHub Actions: Add auto-translated datasets

Upload from GitHub Actions: Merge pull request #18 from datenlabor-bmz/pr-17

Upload from GitHub Actions: Add auto-translated datasets

Upload from GitHub Actions: ran full evaluation locally

Upload from GitHub Actions: minor chashing change

Upload from GitHub Actions: updated and cleaned up scripts for new eval runs

Upload from GitHub Actions: Update models.py, models.json, and results.json with latest evaluation data and model additions

Upload from GitHub Actions: Add Todos for using existing machine-translated datasets rather than our own ones

Upload from GitHub Actions: updated translation functions

Upload from GitHub Actions: import flexibility on backend

Upload from GitHub Actions: fixed import error

Upload from GitHub Actions: updated frontend and backend to fix bugs

Upload from GitHub Actions: Merge pull request #13 from datenlabor-bmz/jn-dev

Upload from GitHub Actions: Merge pull request #10 from datenlabor-bmz/jn-dev

Upload from GitHub Actions: updated batch size and delay

Upload from GitHub Actions: updated workflow settings

Upload from GitHub Actions: Merge pull request #9 from datenlabor-bmz/jn-dev

Upload from GitHub Actions: Merge pull request #7 from datenlabor-bmz/jn-dev

Upload from GitHub Actions: Merge pull request #6 from datenlabor-bmz/jn-dev