Minor tool for comparison of benchmark results (#7974)

benchmark/mmlu/bench_sglang.py

@@ -9,6 +9,7 @@ import tiktoken
 
 from sglang.test.test_utils import (
     add_common_sglang_args_and_parse,
+    dump_bench_raw_result,
     select_sglang_backend,
 )
 
@@ -142,6 +143,13 @@ def main(args):
     assert pt == len(cors)
     weighted_acc = np.mean(cors)
 
+    dump_bench_raw_result(
+        path=args.raw_result_file,
+        states=states,
+        preds=preds,
+        labels=labels,
+    )
+
     # Print results
     print("Total latency: {:.3f}".format(latency))
     print("Average accuracy: {:.3f}".format(weighted_acc))