mirror of
https://github.com/google-gemini/gemini-cli.git
synced 2026-03-10 14:10:37 -07:00
Run evals for all models. (#17123)
This commit is contained in:
committed by
GitHub
parent
8605d0d024
commit
c43b04b44c
9
.github/workflows/evals-nightly.yml
vendored
9
.github/workflows/evals-nightly.yml
vendored
@@ -22,6 +22,12 @@ jobs:
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
model:
|
||||
- 'gemini-3-pro-preview'
|
||||
- 'gemini-3-flash-preview'
|
||||
- 'gemini-2.5-pro'
|
||||
- 'gemini-2.5-flash'
|
||||
- 'gemini-2.5-flash-lite'
|
||||
run_attempt: [1, 2, 3]
|
||||
steps:
|
||||
- name: 'Checkout'
|
||||
@@ -45,6 +51,7 @@ jobs:
|
||||
- name: 'Run Evals'
|
||||
env:
|
||||
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
|
||||
GEMINI_MODEL: '${{ matrix.model }}'
|
||||
RUN_EVALS: "${{ github.event.inputs.run_all != 'false' }}"
|
||||
run: 'npm run test:all_evals'
|
||||
|
||||
@@ -52,7 +59,7 @@ jobs:
|
||||
if: 'always()'
|
||||
uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
|
||||
with:
|
||||
name: 'eval-logs-${{ matrix.run_attempt }}'
|
||||
name: 'eval-logs-${{ matrix.model }}-${{ matrix.run_attempt }}'
|
||||
path: 'evals/logs'
|
||||
retention-days: 7
|
||||
|
||||
|
||||
Reference in New Issue
Block a user