Fixed formatting
Browse files
results/GenericAgent-AgentTrek-1.0-32b/webarena.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
{
|
3 |
"agent_name": "GenericAgent-AgentTrek-1.0-32b",
|
4 |
"study_id": "ac309635-f3fd-417e-ac16-1e0fc943a54f",
|
5 |
-
"date_time": "2025-01-25 10
|
6 |
"benchmark": "WebArena",
|
7 |
"score": 22.4,
|
8 |
"std_err": 1.5,
|
|
|
2 |
{
|
3 |
"agent_name": "GenericAgent-AgentTrek-1.0-32b",
|
4 |
"study_id": "ac309635-f3fd-417e-ac16-1e0fc943a54f",
|
5 |
+
"date_time": "2025-01-25 10:16:41",
|
6 |
"benchmark": "WebArena",
|
7 |
"score": 22.4,
|
8 |
"std_err": 1.5,
|
results/GenericAgent-AgentTrek-1.0-32b/workarena-l1.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"agent_name": "GenericAgent-AgentTrek-1.0-32b",
|
4 |
"study_id": "ed14232c-cd7e-4708-b334-ebaf1f220000",
|
5 |
"date_time": "2025-01-12 00:37:04",
|
6 |
-
"benchmark": "
|
7 |
"score": 38.29,
|
8 |
"std_err": 2.70,
|
9 |
"benchmark_specific": "No",
|
|
|
3 |
"agent_name": "GenericAgent-AgentTrek-1.0-32b",
|
4 |
"study_id": "ed14232c-cd7e-4708-b334-ebaf1f220000",
|
5 |
"date_time": "2025-01-12 00:37:04",
|
6 |
+
"benchmark": "WorkArena-L1",
|
7 |
"score": 38.29,
|
8 |
"std_err": 2.70,
|
9 |
"benchmark_specific": "No",
|
results/GenericAgent-AgentTrek-1.0-32b/workarena-l2.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"agent_name": "GenericAgent-AgentTrek-1.0-32b",
|
4 |
"study_id": "957fb895-8548-46f4-92f0-5de6be7ceb61",
|
5 |
"date_time": "2025-01-12 09:39:21",
|
6 |
-
"benchmark": "
|
7 |
"score": 2.98,
|
8 |
"std_err": 1.10,
|
9 |
"benchmark_specific": "No",
|
|
|
3 |
"agent_name": "GenericAgent-AgentTrek-1.0-32b",
|
4 |
"study_id": "957fb895-8548-46f4-92f0-5de6be7ceb61",
|
5 |
"date_time": "2025-01-12 09:39:21",
|
6 |
+
"benchmark": "WorkArena-L2",
|
7 |
"score": 2.98,
|
8 |
"std_err": 1.10,
|
9 |
"benchmark_specific": "No",
|
results/GenericAgent-AgentTrek-1.0-32b/workarena-l3.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"agent_name": "GenericAgent-AgentTrek-1.0-32b",
|
4 |
"study_id": "a951b33f-d118-4cf4-a2ef-cc2ef204eeb0",
|
5 |
"date_time": "2025-01-13 12:11:45",
|
6 |
-
"benchmark": "
|
7 |
"score": 0.0,
|
8 |
"std_err": 0.0,
|
9 |
"benchmark_specific": "No",
|
|
|
3 |
"agent_name": "GenericAgent-AgentTrek-1.0-32b",
|
4 |
"study_id": "a951b33f-d118-4cf4-a2ef-cc2ef204eeb0",
|
5 |
"date_time": "2025-01-13 12:11:45",
|
6 |
+
"benchmark": "WorkArena-L3",
|
7 |
"score": 0.0,
|
8 |
"std_err": 0.0,
|
9 |
"benchmark_specific": "No",
|