Spaces:
Running
Running
Upload from GitHub Actions: added new models
Browse files- evals/models.py +3 -0
evals/models.py
CHANGED
|
@@ -14,11 +14,13 @@ from requests import HTTPError, get
|
|
| 14 |
# for development purposes, all languages will be evaluated on the fast models
|
| 15 |
# and only a sample of languages will be evaluated on all models
|
| 16 |
important_models = [
|
|
|
|
| 17 |
"meta-llama/llama-4-maverick", # 0.6$
|
| 18 |
"meta-llama/llama-3.3-70b-instruct", # 0.3$
|
| 19 |
"meta-llama/llama-3.1-70b-instruct", # 0.3$
|
| 20 |
"meta-llama/llama-3-70b-instruct", # 0.4$
|
| 21 |
# "meta-llama/llama-2-70b-chat", # 0.9$; not properly supported by OpenRouter
|
|
|
|
| 22 |
"openai/gpt-5.1",
|
| 23 |
"openai/gpt-5",
|
| 24 |
"openai/gpt-5-mini",
|
|
@@ -27,6 +29,7 @@ important_models = [
|
|
| 27 |
"openai/gpt-4o", # 10$
|
| 28 |
"openai/gpt-3.5-turbo", # $1.50
|
| 29 |
"openai/gpt-oss-120b",
|
|
|
|
| 30 |
"anthropic/claude-opus-4.5", # 25$
|
| 31 |
"anthropic/claude-sonnet-4.5",
|
| 32 |
"anthropic/claude-haiku-4.5",
|
|
|
|
| 14 |
# for development purposes, all languages will be evaluated on the fast models
|
| 15 |
# and only a sample of languages will be evaluated on all models
|
| 16 |
important_models = [
|
| 17 |
+
"allenai/olmo-3.1-32b-instruct",
|
| 18 |
"meta-llama/llama-4-maverick", # 0.6$
|
| 19 |
"meta-llama/llama-3.3-70b-instruct", # 0.3$
|
| 20 |
"meta-llama/llama-3.1-70b-instruct", # 0.3$
|
| 21 |
"meta-llama/llama-3-70b-instruct", # 0.4$
|
| 22 |
# "meta-llama/llama-2-70b-chat", # 0.9$; not properly supported by OpenRouter
|
| 23 |
+
"openai/gpt-5.2",
|
| 24 |
"openai/gpt-5.1",
|
| 25 |
"openai/gpt-5",
|
| 26 |
"openai/gpt-5-mini",
|
|
|
|
| 29 |
"openai/gpt-4o", # 10$
|
| 30 |
"openai/gpt-3.5-turbo", # $1.50
|
| 31 |
"openai/gpt-oss-120b",
|
| 32 |
+
"anthropic/claude-opus-4.6", # 25$
|
| 33 |
"anthropic/claude-opus-4.5", # 25$
|
| 34 |
"anthropic/claude-sonnet-4.5",
|
| 35 |
"anthropic/claude-haiku-4.5",
|