diff --git a/experiments/outputs/_leaderboard.json b/experiments/outputs/_leaderboard.json index d34fcd1..7134f5f 100644 --- a/experiments/outputs/_leaderboard.json +++ b/experiments/outputs/_leaderboard.json @@ -796,5 +796,62 @@ "interactions": 26.61 } } + }, + { + "id": "5509efd4-3e4bf4e2", + "method": { + "name": "temp", + "tooltip": "temp" + }, + "llm": { + "name": "temp", + "tooltip": "temp" + }, + "url": "temp", + "date": "2024-11-29", + "test_normal": { + "all": { + "task_goal_completion": 9.5, + "scenario_goal_completion": 7.1, + "interactions": 3.32 + }, + "level 1": { + "task_goal_completion": 28.1, + "scenario_goal_completion": 21.1, + "interactions": 3.32 + }, + "level 2": { + "task_goal_completion": 0.0, + "scenario_goal_completion": 0.0, + "interactions": 3.32 + }, + "level 3": { + "task_goal_completion": 0.0, + "scenario_goal_completion": 0.0, + "interactions": 3.32 + } + }, + "test_challenge": { + "all": { + "task_goal_completion": 5.5, + "scenario_goal_completion": 4.3, + "interactions": 4.39 + }, + "level 1": { + "task_goal_completion": 26.4, + "scenario_goal_completion": 20.8, + "interactions": 4.39 + }, + "level 2": { + "task_goal_completion": 2.7, + "scenario_goal_completion": 2.0, + "interactions": 4.39 + }, + "level 3": { + "task_goal_completion": 0.0, + "scenario_goal_completion": 0.0, + "interactions": 4.39 + } + } } ] \ No newline at end of file diff --git a/experiments/outputs/temp_test_test_challenge/leaderboard.bundle b/experiments/outputs/temp_test_test_challenge/leaderboard.bundle new file mode 100644 index 0000000..bc230d8 --- /dev/null +++ b/experiments/outputs/temp_test_test_challenge/leaderboard.bundle @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8469dc68c9fa729812b9bd211372be114db295133795c8e12b07ebcf49cf4fad +size 4345350 diff --git a/experiments/outputs/temp_test_test_normal/leaderboard.bundle b/experiments/outputs/temp_test_test_normal/leaderboard.bundle new file mode 100644 index 0000000..300f3bb --- /dev/null +++ b/experiments/outputs/temp_test_test_normal/leaderboard.bundle @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f4b86218d4b23281a9b6f01f081bad74385facd30e8b801471841a363a539b6 +size 1822089