Removed old results files
Browse files- app.py +1 -1
- results/Bgym-GPT-3.5/results.json +0 -53
- results/Bgym-GPT-4o-V/results.json +0 -52
- results/Bgym-GPT-4o/results.json +0 -52
- results/Bgym-Llama-3-70b/results.json +0 -52
- results/Bgym-Mixtral-8x22b/results.json +0 -52
app.py
CHANGED
@@ -130,7 +130,7 @@ def check_sanity(agent):
|
|
130 |
return True
|
131 |
|
132 |
def main():
|
133 |
-
st.set_page_config(page_title="
|
134 |
|
135 |
all_agents = os.listdir("results")
|
136 |
all_results = {}
|
|
|
130 |
return True
|
131 |
|
132 |
def main():
|
133 |
+
st.set_page_config(page_title="BrowserGym Leaderboard", layout="wide")
|
134 |
|
135 |
all_agents = os.listdir("results")
|
136 |
all_results = {}
|
results/Bgym-GPT-3.5/results.json
DELETED
@@ -1,53 +0,0 @@
|
|
1 |
-
[
|
2 |
-
{
|
3 |
-
"benchmark": "WorkArena-L1",
|
4 |
-
"score": 6.1,
|
5 |
-
"std_err": 0.3,
|
6 |
-
"benchmark_specific": "No",
|
7 |
-
"benchmark_tuned": "No",
|
8 |
-
"followed_evaluation_protocol": "Yes",
|
9 |
-
"reproducible": "Yes",
|
10 |
-
"reproduced": [["aug 2025", 0.65, 0.05, "study_id"]],
|
11 |
-
"comments": "NA"
|
12 |
-
},
|
13 |
-
{
|
14 |
-
"benchmark": "WorkArena++-L2",
|
15 |
-
"score": 0.0,
|
16 |
-
"std_err": 0.0,
|
17 |
-
"benchmark_specific": "No",
|
18 |
-
"benchmark_tuned": "No",
|
19 |
-
"followed_evaluation_protocol": "Yes",
|
20 |
-
"reproducible": "Yes",
|
21 |
-
"comments": "NA"
|
22 |
-
},
|
23 |
-
{
|
24 |
-
"benchmark": "WorkArena++-L3",
|
25 |
-
"score": 0.0,
|
26 |
-
"std_err": 0.0,
|
27 |
-
"benchmark_specific": "No",
|
28 |
-
"benchmark_tuned": "No",
|
29 |
-
"followed_evaluation_protocol": "Yes",
|
30 |
-
"reproducible": "Yes",
|
31 |
-
"comments": "NA"
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"benchmark": "MiniWoB",
|
35 |
-
"score": 43.4,
|
36 |
-
"std_err": 0.1,
|
37 |
-
"benchmark_specific": "No",
|
38 |
-
"benchmark_tuned": "No",
|
39 |
-
"followed_evaluation_protocol": "Yes",
|
40 |
-
"reproducible": "Yes",
|
41 |
-
"comments": "NA"
|
42 |
-
},
|
43 |
-
{
|
44 |
-
"benchmark": "WebArena",
|
45 |
-
"score": 6.7,
|
46 |
-
"std_err": 0.2,
|
47 |
-
"benchmark_specific": "No",
|
48 |
-
"benchmark_tuned": "No",
|
49 |
-
"followed_evaluation_protocol": "Yes",
|
50 |
-
"reproducible": "Yes",
|
51 |
-
"comments": "NA"
|
52 |
-
}
|
53 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
results/Bgym-GPT-4o-V/results.json
DELETED
@@ -1,52 +0,0 @@
|
|
1 |
-
[
|
2 |
-
{
|
3 |
-
"benchmark": "WorkArena-L1",
|
4 |
-
"score": 41.8,
|
5 |
-
"std_err": 0.4,
|
6 |
-
"benchmark_specific": "No",
|
7 |
-
"benchmark_tuned": "No",
|
8 |
-
"followed_evaluation_protocol": "Yes",
|
9 |
-
"reproducible": "Yes",
|
10 |
-
"comments": "NA"
|
11 |
-
},
|
12 |
-
{
|
13 |
-
"benchmark": "WorkArena++-L2",
|
14 |
-
"score": 3.8,
|
15 |
-
"std_err": 0.6,
|
16 |
-
"benchmark_specific": "No",
|
17 |
-
"benchmark_tuned": "No",
|
18 |
-
"followed_evaluation_protocol": "Yes",
|
19 |
-
"reproducible": "Yes",
|
20 |
-
"comments": "NA"
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"benchmark": "WorkArena++-L3",
|
24 |
-
"score": 0.0,
|
25 |
-
"std_err": 0.0,
|
26 |
-
"benchmark_specific": "No",
|
27 |
-
"benchmark_tuned": "No",
|
28 |
-
"followed_evaluation_protocol": "Yes",
|
29 |
-
"reproducible": "Yes",
|
30 |
-
"comments": "NA"
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"benchmark": "MiniWoB",
|
34 |
-
"score": 72.5,
|
35 |
-
"std_err": 0.5,
|
36 |
-
"benchmark_specific": "No",
|
37 |
-
"benchmark_tuned": "No",
|
38 |
-
"followed_evaluation_protocol": "Yes",
|
39 |
-
"reproducible": "Yes",
|
40 |
-
"comments": "NA"
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"benchmark": "WebArena",
|
44 |
-
"score": 24.0,
|
45 |
-
"std_err": 0.4,
|
46 |
-
"benchmark_specific": "No",
|
47 |
-
"benchmark_tuned": "No",
|
48 |
-
"followed_evaluation_protocol": "Yes",
|
49 |
-
"reproducible": "Yes",
|
50 |
-
"comments": "NA"
|
51 |
-
}
|
52 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
results/Bgym-GPT-4o/results.json
DELETED
@@ -1,52 +0,0 @@
|
|
1 |
-
[
|
2 |
-
{
|
3 |
-
"benchmark": "WorkArena-L1",
|
4 |
-
"score": 42.7,
|
5 |
-
"std_err": 0.4,
|
6 |
-
"benchmark_specific": "No",
|
7 |
-
"benchmark_tuned": "No",
|
8 |
-
"followed_evaluation_protocol": "Yes",
|
9 |
-
"reproducible": "Yes",
|
10 |
-
"comments": "NA"
|
11 |
-
},
|
12 |
-
{
|
13 |
-
"benchmark": "WorkArena++-L2",
|
14 |
-
"score": 3.0,
|
15 |
-
"std_err": 0.6,
|
16 |
-
"benchmark_specific": "No",
|
17 |
-
"benchmark_tuned": "No",
|
18 |
-
"followed_evaluation_protocol": "Yes",
|
19 |
-
"reproducible": "Yes",
|
20 |
-
"comments": "NA"
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"benchmark": "WorkArena++-L3",
|
24 |
-
"score": 0.0,
|
25 |
-
"std_err": 0.0,
|
26 |
-
"benchmark_specific": "No",
|
27 |
-
"benchmark_tuned": "No",
|
28 |
-
"followed_evaluation_protocol": "Yes",
|
29 |
-
"reproducible": "Yes",
|
30 |
-
"comments": "NA"
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"benchmark": "MiniWoB",
|
34 |
-
"score": 71.3,
|
35 |
-
"std_err": 0.5,
|
36 |
-
"benchmark_specific": "No",
|
37 |
-
"benchmark_tuned": "No",
|
38 |
-
"followed_evaluation_protocol": "Yes",
|
39 |
-
"reproducible": "Yes",
|
40 |
-
"comments": "NA"
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"benchmark": "WebArena",
|
44 |
-
"score": 23.5,
|
45 |
-
"std_err": 0.4,
|
46 |
-
"benchmark_specific": "No",
|
47 |
-
"benchmark_tuned": "No",
|
48 |
-
"followed_evaluation_protocol": "Yes",
|
49 |
-
"reproducible": "Yes",
|
50 |
-
"comments": "NA"
|
51 |
-
}
|
52 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
results/Bgym-Llama-3-70b/results.json
DELETED
@@ -1,52 +0,0 @@
|
|
1 |
-
[
|
2 |
-
{
|
3 |
-
"benchmark": "WorkArena-L1",
|
4 |
-
"score": 17.9,
|
5 |
-
"std_err": 0.6,
|
6 |
-
"benchmark_specific": "No",
|
7 |
-
"benchmark_tuned": "No",
|
8 |
-
"followed_evaluation_protocol": "Yes",
|
9 |
-
"reproducible": "Yes",
|
10 |
-
"comments": "NA"
|
11 |
-
},
|
12 |
-
{
|
13 |
-
"benchmark": "WorkArena++-L2",
|
14 |
-
"score": 0.0,
|
15 |
-
"std_err": 0.0,
|
16 |
-
"benchmark_specific": "No",
|
17 |
-
"benchmark_tuned": "No",
|
18 |
-
"followed_evaluation_protocol": "Yes",
|
19 |
-
"reproducible": "Yes",
|
20 |
-
"comments": "NA"
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"benchmark": "WorkArena++-L3",
|
24 |
-
"score": 0.0,
|
25 |
-
"std_err": 0.0,
|
26 |
-
"benchmark_specific": "No",
|
27 |
-
"benchmark_tuned": "No",
|
28 |
-
"followed_evaluation_protocol": "Yes",
|
29 |
-
"reproducible": "Yes",
|
30 |
-
"comments": "NA"
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"benchmark": "MiniWoB",
|
34 |
-
"score": 68.2,
|
35 |
-
"std_err": 0.7,
|
36 |
-
"benchmark_specific": "No",
|
37 |
-
"benchmark_tuned": "No",
|
38 |
-
"followed_evaluation_protocol": "Yes",
|
39 |
-
"reproducible": "Yes",
|
40 |
-
"comments": "NA"
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"benchmark": "WebArena",
|
44 |
-
"score": 11.0,
|
45 |
-
"std_err": 0.3,
|
46 |
-
"benchmark_specific": "No",
|
47 |
-
"benchmark_tuned": "No",
|
48 |
-
"followed_evaluation_protocol": "Yes",
|
49 |
-
"reproducible": "Yes",
|
50 |
-
"comments": "NA"
|
51 |
-
}
|
52 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
results/Bgym-Mixtral-8x22b/results.json
DELETED
@@ -1,52 +0,0 @@
|
|
1 |
-
[
|
2 |
-
{
|
3 |
-
"benchmark": "WorkArena-L1",
|
4 |
-
"score": 12.4,
|
5 |
-
"std_err": 0.7,
|
6 |
-
"benchmark_specific": "No",
|
7 |
-
"benchmark_tuned": "No",
|
8 |
-
"followed_evaluation_protocol": "Yes",
|
9 |
-
"reproducible": "Yes",
|
10 |
-
"comments": "NA"
|
11 |
-
},
|
12 |
-
{
|
13 |
-
"benchmark": "WorkArena++-L2",
|
14 |
-
"score": 0.0,
|
15 |
-
"std_err": 0.0,
|
16 |
-
"benchmark_specific": "No",
|
17 |
-
"benchmark_tuned": "No",
|
18 |
-
"followed_evaluation_protocol": "Yes",
|
19 |
-
"reproducible": "Yes",
|
20 |
-
"comments": "NA"
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"benchmark": "WorkArena++-L3",
|
24 |
-
"score": 0.0,
|
25 |
-
"std_err": 0.0,
|
26 |
-
"benchmark_specific": "No",
|
27 |
-
"benchmark_tuned": "No",
|
28 |
-
"followed_evaluation_protocol": "Yes",
|
29 |
-
"reproducible": "Yes",
|
30 |
-
"comments": "NA"
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"benchmark": "MiniWoB",
|
34 |
-
"score": 62.4,
|
35 |
-
"std_err": 0.5,
|
36 |
-
"benchmark_specific": "No",
|
37 |
-
"benchmark_tuned": "No",
|
38 |
-
"followed_evaluation_protocol": "Yes",
|
39 |
-
"reproducible": "Yes",
|
40 |
-
"comments": "NA"
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"benchmark": "WebArena",
|
44 |
-
"score": 12.6,
|
45 |
-
"std_err": 0.9,
|
46 |
-
"benchmark_specific": "No",
|
47 |
-
"benchmark_tuned": "No",
|
48 |
-
"followed_evaluation_protocol": "Yes",
|
49 |
-
"reproducible": "Yes",
|
50 |
-
"comments": "NA"
|
51 |
-
}
|
52 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|