Skip to content

Commit 6088226

Browse files
committed
feat: add openai gpt-5 benchmark
1 parent cb62424 commit 6088226

2 files changed

Lines changed: 1642 additions & 1 deletion

File tree

data/benchmarks/v0.8.1/default/leaderboard.json

Lines changed: 55 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,60 @@
11
{
2-
"generated_at": 1757522204,
2+
"generated_at": 1757527431,
33
"entries": [
4+
{
5+
"runs": 20,
6+
"wins": 0,
7+
"completed": 16,
8+
"avg_final_round": 4.85,
9+
"std_dev_final_round": 2.277463963548745,
10+
"providers": {
11+
"OpenAI": 770,
12+
"Azure": 1
13+
},
14+
"calls": {
15+
"successful": 737,
16+
"error": 1,
17+
"failed": 33,
18+
"total": 771
19+
},
20+
"total": {
21+
"input_tokens": 1686541,
22+
"output_tokens": 1524415,
23+
"input_cost": 0.89742425,
24+
"output_cost": 15.24415,
25+
"total_cost": 16.14157425,
26+
"time_ms": 35910504
27+
},
28+
"average": {
29+
"input_tokens": 2187.472114137484,
30+
"output_tokens": 1977.1919584954605,
31+
"input_cost": 0.001163974383916991,
32+
"output_cost": 0.019771919584954604,
33+
"total_cost": 0.020935893968871598,
34+
"time_ms": 46576.52918287938
35+
},
36+
"std_dev": {
37+
"input_tokens": 436.4503871634609,
38+
"output_tokens": 1053.2986759539856,
39+
"input_cost": 0.0005858397770650825,
40+
"output_cost": 0.010532986759539856,
41+
"total_cost": 0.010632784286617479,
42+
"time_ms": 24515.108007318897
43+
},
44+
"config": {
45+
"model": "openai/gpt-5",
46+
"strategy": "default",
47+
"deck": "Red Deck",
48+
"stake": 1,
49+
"seed": "OOOO155",
50+
"challenge": null,
51+
"version": "0.8.2",
52+
"name": "Unknown Name",
53+
"description": "Unknown Description",
54+
"author": "BalatroBench",
55+
"tags": []
56+
}
57+
},
458
{
559
"runs": 17,
660
"wins": 0,

0 commit comments

Comments
 (0)