Release MMLU v1.10.0, Lite v1.10.0, AIR-Bench v1.2.0 (#3140)

stanford-crfm · Nov 7, 2024 · a05c4b0 · a05c4b0
1 parent a40c760
commit a05c4b0
Showing 1 changed file with 3 additions and 3 deletions.
diff --git a/helm-frontend/project_metadata.json b/helm-frontend/project_metadata.json
@@ -3,7 +3,7 @@
 		"title": "Lite",
 		"description": "Lightweight, broad evaluation of the capabilities of language models using in-context learning",
 		"id": "lite",
-		"releases": ["v1.9.0", "v1.8.0", "v1.7.0", "v1.6.0", "v1.5.0", "v1.4.0", "v1.3.0", "v1.2.0", "v1.1.0", "v1.0.0"]
+		"releases": ["v1.10.0", "v1.9.0", "v1.8.0", "v1.7.0", "v1.6.0", "v1.5.0", "v1.4.0", "v1.3.0", "v1.2.0", "v1.1.0", "v1.0.0"]
 	},
 	{
 		"title": "Classic",
@@ -27,7 +27,7 @@
 		"title": "MMLU",
 		"description": "Massive Multitask Language Understanding (MMLU) evaluations using standardized prompts",
 		"id": "mmlu",
-		"releases": ["v1.9.0", "v1.8.0", "v1.7.0", "v1.6.0", "v1.5.0", "v1.4.0", "v1.3.0", "v1.2.0", "v1.1.0", "v1.0.0"]
+		"releases": ["v1.10.0", "v1.9.0", "v1.8.0", "v1.7.0", "v1.6.0", "v1.5.0", "v1.4.0", "v1.3.0", "v1.2.0", "v1.1.0", "v1.0.0"]
 	},
 	{
 		"title": "VHELM",
@@ -45,7 +45,7 @@
 		"title": "AIR-Bench",
 		"description": "Safety benchmark based on emerging government regulations and company policies",
 		"id": "air-bench",
-		"releases": ["v1.1.0", "v1.0.0"]
+		"releases": ["v1.2.0", "v1.1.0", "v1.0.0"]
 	},
 	{
 		"title": "CLEVA",