[Benchmark] Add GSM8K Platinum Eval (#14565)

This commit is contained in:
b8zhong
2026-01-16 11:06:14 +08:00
committed by GitHub
parent e7dc85c50b
commit d44f09ad98
3 changed files with 46 additions and 10 deletions
+19 -6
View File
@@ -6,6 +6,7 @@ import re
import time
import numpy as np
from datasets import load_dataset
from sglang.lang.api import set_default_backend
from sglang.test.test_utils import (
@@ -48,11 +49,18 @@ def main(args):
set_default_backend(select_sglang_backend(args))
# Read data
data_path = args.data_path
url = "https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl"
if not os.path.isfile(data_path):
data_path = download_and_cache_file(url)
lines = list(read_jsonl(data_path))
if args.platinum:
print("Loading GSM8K Platinum dataset from HuggingFace...")
dataset = load_dataset("madrylab/gsm8k-platinum", "main", split="test")
lines = [
{"question": item["question"], "answer": item["answer"]} for item in dataset
]
else:
data_path = args.data_path
url = "https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl"
if not os.path.isfile(data_path):
data_path = download_and_cache_file(url)
lines = list(read_jsonl(data_path))
# Construct prompts
num_questions = args.num_questions
@@ -125,7 +133,7 @@ def main(args):
with open(args.result_file, "a") as fout:
value = {
"task": "gsm8k",
"task": "gsm8k-platinum" if args.platinum else "gsm8k",
"backend": args.backend,
"num_gpus": 1,
"latency": round(latency, 3),
@@ -144,5 +152,10 @@ if __name__ == "__main__":
parser.add_argument("--num-shots", type=int, default=5)
parser.add_argument("--data-path", type=str, default="test.jsonl")
parser.add_argument("--num-questions", type=int, default=200)
parser.add_argument(
"--platinum",
action="store_true",
help="Use GSM8K Platinum dataset (drop-in replacement with corrected labels)",
)
args = add_common_sglang_args_and_parse(parser)
main(args)