reasoning-gym/eval/results/summary_openai_o1_20250212_103017.json
Zafir Stojanovski 58a641e59f lint
2025-02-12 11:21:46 +01:00

61 lines
1.3 KiB
JSON

[
{
"dataset_name": "letter_counting",
"model": "openai/o1",
"average_score": 0.99,
"total_examples": 50,
"timestamp": "2025-02-12T10:26:39.897674",
"config": {
"min_words": 5,
"max_words": 15,
"size": 50,
"seed": 42
}
},
{
"dataset_name": "propositional_logic",
"model": "openai/o1",
"average_score": 0.010000000000000004,
"total_examples": 50,
"timestamp": "2025-02-12T10:27:45.054740",
"config": {
"size": 50,
"seed": 42
}
},
{
"dataset_name": "leg_counting",
"model": "openai/o1",
"average_score": 0.802,
"total_examples": 50,
"timestamp": "2025-02-12T10:28:06.199253",
"config": {
"min_animals": 3,
"max_animals": 8,
"size": 50,
"seed": 42
}
},
{
"dataset_name": "group_anagrams",
"model": "openai/o1",
"average_score": 0.94,
"total_examples": 50,
"timestamp": "2025-02-12T10:30:02.084562",
"config": {
"size": 50,
"seed": 42
}
},
{
"dataset_name": "spell_backward",
"model": "openai/o1",
"average_score": 0.9802000000000001,
"total_examples": 50,
"timestamp": "2025-02-12T10:30:17.839014",
"config": {
"size": 50,
"seed": 42
}
}
]