eval-protocol
diff --git a/‎eval_protocol/quickstart/llm_judge.py‎
Lines changed: 1 addition & 1 deletion b/‎eval_protocol/quickstart/llm_judge.py‎
Lines changed: 1 addition & 1 deletion
@@ -50,7 +50,7 @@ def aime2025_dataset_adapter(rows: List[Dict[str, Any]]) -> List[EvaluationRow]:
         # {
         #     "model": "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507",
         # },
-        {"model": "gpt-4.1"},
+        # {"model": "gpt-4.1"},
         {
             "max_tokens": 131000,
             "extra_body": {"reasoning_effort": "medium"},
Original file line number	Diff line number	Diff line change
`@@ -50,7 +50,7 @@ def aime2025_dataset_adapter(rows: List[Dict[str, Any]]) -> List[EvaluationRow]:`
`50`	`50`	`# {`
`51`	`51`	`# "model": "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507",`
`52`	`52`	`# },`
`53`		`- {"model": "gpt-4.1"},`
	`53`	`+ # {"model": "gpt-4.1"},`
`54`	`54`	`{`
`55`	`55`	`"max_tokens": 131000,`
`56`	`56`	`"extra_body": {"reasoning_effort": "medium"},`