Skip to content

Commit ec8a6db

Browse files
authored
Merge pull request #64 from get-convex/jordan/add-gemini-pro
Add gemini pro to evals
2 parents f1b70a3 + b411bc6 commit ec8a6db

File tree

3 files changed

+10
-1
lines changed

3 files changed

+10
-1
lines changed

.github/workflows/daily_google_evals.yml

+1-1
Original file line numberDiff line numberDiff line change
@@ -46,7 +46,7 @@ jobs:
4646
4747
- name: Set Google models
4848
run: |
49-
echo "MODELS=gemini-2.0-flash-lite,gemini-2.0-flash,gemini-1.5-flash" >> $GITHUB_ENV
49+
echo "MODELS=gemini-2.0-flash-lite,gemini-2.0-flash,gemini-1.5-flash,gemini-2.5-pro-exp-03-25" >> $GITHUB_ENV
5050
5151
- name: Run evaluations
5252
env:

runner/eval_convex_coding.py

+1
Original file line numberDiff line numberDiff line change
@@ -206,6 +206,7 @@ def convex_coding_task(model: ModelTemplate, input: str):
206206
"o3-mini",
207207
"gemini-2.0-flash-lite",
208208
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
209+
"gemini-2.5-pro-exp-03-25",
209210
]
210211

211212
if os.getenv("MODELS") is not None:

runner/models/__init__.py

+8
Original file line numberDiff line numberDiff line change
@@ -132,6 +132,14 @@ class ModelTemplate(BaseModel):
132132
uses_system_prompt=False,
133133
provider=ModelProvider.GOOGLE,
134134
),
135+
ModelTemplate(
136+
name="gemini-2.5-pro-exp-03-25",
137+
formatted_name="Gemini 2.5 Pro (Experimental)",
138+
max_concurrency=int(os.getenv("GOOGLE_CONCURRENCY", "4")),
139+
requires_chain_of_thought=False,
140+
uses_system_prompt=False,
141+
provider=ModelProvider.GOOGLE,
142+
),
135143
]
136144
MODELS_BY_NAME = {model.name: model for model in ALL_MODELS}
137145

0 commit comments

Comments
 (0)