doc_id int64 | doc string | target string | arguments string | exact_match int64 | extracted_answers string | source_file string | info string | eval_type string | response_to_evaluate string | row_idx int64 | gen_idx int64 | eval_extracted_answer string | answer_extraction_llm_prompt string | answer_extraction_reasoning string | answer_idx int64 | answer_is_correct bool | answer_judgement_reasoning string | answer_judgement_llm_prompt string | internal_answers_per_gen sequence | internal_answers_is_correct_per_gen sequence | internal_answers_judgement_reasoning_per_gen sequence | internal_answers_judgement_llm_prompt_per_gen sequence | responses_to_evaluate sequence | eval_extracted_answers sequence | answer_is_corrects sequence | answer_reasons sequence | mock_budget_force_convo list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | "{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED) | 157 | "{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED) | 0 | [false] | samples_countdown4arg_2025-06-21T08-27-35.766260.jsonl | "[{\"budget_forced_chunks\": [\"1. First, let's try adding 55 and 60 together:\\n55 + 60 = 115\\nNow(...TRUNCATED) | countdown | "1. First, let's try adding 55 and 60 together:\n55 + 60 = 115\nNow we need to add 36 to this result(...TRUNCATED) | 0 | 0 | <answer>
Step 1: 55 + 60 = 115
Step 2: 115 + 36 = 151
Step 3: 151 + 6 = 157 | "Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED) | 0 | true | [["<answer>\nStep 1: 55 + 60 = 115\nStep 2: 115 + 36 = 151\nStep 3: 151 + 6 = 157","<answer>\nStep 1(...TRUNCATED) | [
[
true,
false,
false,
false,
false,
true
],
[
false
],
[
false
],
[
false,
false,
false
],
[
false,
false,
false,
false
]
] | [["","Incorrect final answer","Incorrect final answer","Incorrect final answer","Incorrect final ans(...TRUNCATED) | [
[
"",
"",
"",
"",
"",
""
],
[
""
],
[
""
],
[
"",
"",
""
],
[
"",
"",
"",
""
]
] | ["1. First, let's try adding 55 and 60 together:\n55 + 60 = 115\nNow we need to add 36 to this resul(...TRUNCATED) | ["<answer>\nStep 1: 55 + 60 + 36 + 6 = 157","157","157","<answer>\nStep 1: 60 / 6 = 10\nStep 2: 10 -(...TRUNCATED) | [
true,
false,
false,
false,
false
] | ["","Expected a single '=' separating expression and result","Expected a single '=' separating expre(...TRUNCATED) | [{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: <answer>\nStep 1: 55 + 60 +(...TRUNCATED) | |||
1 | "{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED) | 109 | "{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED) | 0 | [false] | samples_countdown4arg_2025-06-21T08-27-35.766260.jsonl | "[{\"budget_forced_chunks\": [\"To solve the problem, we need to use the numbers [83, 41, 3, 18] and(...TRUNCATED) | countdown | "To solve the problem, we need to use the numbers [83, 41, 3, 18] and apply basic arithmetic operati(...TRUNCATED) | 1 | 0 | <answer>
Step 1: 83 - 41 = 42
Step 2: 42 + 18 = 60 | "Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED) | 0 | false | Incorrect final answer | [["<answer>\nStep 1: 83 - 41 = 42\nStep 2: 42 + 18 = 60","<answer>\nStep 1: 83 - 41 = 42\nStep 2: 42(...TRUNCATED) | [
[
false,
false,
false,
false,
false,
false
],
[
false,
false,
false
]
] | [["Incorrect final answer","Incorrect final answer","Incorrect final answer","Incorrect final answer(...TRUNCATED) | [
[
"",
"",
"",
"",
"",
""
],
[
"",
"",
""
]
] | ["To solve the problem, we need to use the numbers [83, 41, 3, 18] and apply basic arithmetic operat(...TRUNCATED) | ["<answer>\nStep 1: 83 + 18 = 101\nStep 2: 101 * 1 = 101","<answer>\nStep 1: 83 - 3 = 80\nStep 2: 80(...TRUNCATED) | [
false,
false
] | [
"Line uses unavailable numbers: Step 2: 101 * 1 = 101",
"Incorrect final answer"
] | [{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: <answer>\nStep 1: 83 + 18 =(...TRUNCATED) | ||
2 | "{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED) | 204 | "{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED) | 0 | [false] | samples_countdown4arg_2025-06-21T08-27-35.766260.jsonl | "[{\"budget_forced_chunks\": [\"1. First, we need to combine the numbers 28 and 100 together. Let's (...TRUNCATED) | countdown | "1. First, we need to combine the numbers 28 and 100 together. Let's start with 28 + 100 = 128.\nNow(...TRUNCATED) | 2 | 0 | <answer>
Step 1: 100 - 30 = 70
Step 2: 70 + 28 = 98 | "Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED) | 0 | false | Incorrect final answer | [["<answer>\nStep 1: 100 - 30 = 70\nStep 2: 70 + 28 = 98","<answer>\nStep 1: 100 - 28 = 72\nStep 2: (...TRUNCATED) | [
[
false,
false,
false,
false,
false
],
[
false,
false,
false,
false,
false,
false,
false,
false
]
] | [["Incorrect final answer","Incorrect final answer","Incorrect final answer","Incorrect final answer(...TRUNCATED) | [
[
"",
"",
"",
"",
""
],
[
"",
"",
"",
"",
"",
"",
"",
""
]
] | ["1. First, we need to combine the numbers 28 and 100 together. Let's start with 28 + 100 = 128.\nNo(...TRUNCATED) | ["<answer>\nStep 1: 100 + 30 = 130\nStep 2: 130 + 28 = 158","<answer>\nStep 1: 100 - 28 = 72\nStep 2(...TRUNCATED) | [
false,
false
] | [
"Incorrect final answer",
"Incorrect final answer"
] | [{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: <answer>\nStep 1: 100 + 30 (...TRUNCATED) | ||
3 | "{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED) | 837 | "{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED) | 0 | [false] | samples_countdown4arg_2025-06-21T08-27-35.766260.jsonl | "[{\"budget_forced_chunks\": [\"To solve this problem, we need to use the numbers [77, 22, 93, 46] a(...TRUNCATED) | countdown | "To solve this problem, we need to use the numbers [77, 22, 93, 46] and apply basic arithmetic opera(...TRUNCATED) | 3 | 0 | <answer>
Step 1: 77 + 46 = 123
Step 2: 123 + 93 = 216 | "Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED) | 0 | false | Incorrect final answer | [["<answer>\nStep 1: 77 + 46 = 123\nStep 2: 123 + 93 = 216","<answer>\nStep 1: 77 + 93 = 170\nStep 2(...TRUNCATED) | [
[
false,
false,
false,
false,
false
]
] | [["Incorrect final answer","Incorrect final answer","Incorrect final answer","Incorrect arithmetic i(...TRUNCATED) | [
[
"",
"",
"",
"",
""
]
] | ["To solve this problem, we need to use the numbers [77, 22, 93, 46] and apply basic arithmetic oper(...TRUNCATED) | [
"<answer>\nStep 1: 77 + 22 = 99\nStep 2: 99 * 93 = 9207\nStep 3: 9207 - 46 = 9161"
] | [
false
] | [
"Incorrect final answer"
] | [{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: <answer>\nStep 1: 77 + 22 =(...TRUNCATED) | ||
4 | "{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED) | 224 | "{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED) | 0 | [false] | samples_countdown4arg_2025-06-21T08-27-35.766260.jsonl | "[{\"budget_forced_chunks\": [\"To solve this problem, we need to use the numbers [31, 44, 21, 28] a(...TRUNCATED) | countdown | "To solve this problem, we need to use the numbers [31, 44, 21, 28] and apply basic arithmetic opera(...TRUNCATED) | 4 | 0 | <answer>
Step 1: 44 + 31 = 75
Step 2: 75 * 21 = 1575 | "Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED) | 0 | false | Incorrect final answer | [["<answer>\nStep 1: 44 + 31 = 75\nStep 2: 75 * 21 = 1575","<answer>\nStep 1: 44 + 21 = 65\nStep 2: (...TRUNCATED) | [
[
false,
false,
false,
false,
false,
false
],
[
false,
false,
false,
false
],
[
false,
false
]
] | [["Incorrect final answer","Line uses unavailable numbers: Step 2: 65 * 44 = 2860","Incorrect final (...TRUNCATED) | [
[
"",
"",
"",
"",
"",
""
],
[
"",
"",
"",
""
],
[
"",
""
]
] | ["To solve this problem, we need to use the numbers [31, 44, 21, 28] and apply basic arithmetic oper(...TRUNCATED) | ["<answer>\nStep 1: 44 - 31 = 13\nStep 2: 13 * 28 = 364","<answer>\nStep 1: 44 + 28 = 72\nStep 2: 72(...TRUNCATED) | [
false,
false,
false
] | [
"Incorrect final answer",
"Incorrect final answer",
"Incorrect final answer"
] | [{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: <answer>\nStep 1: 44 - 31 =(...TRUNCATED) | ||
5 | "{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED) | 358 | "{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED) | 0 | [false] | samples_countdown4arg_2025-06-21T08-27-35.766260.jsonl | "[{\"budget_forced_chunks\": [\"To solve the problem, we need to use the numbers [44, 5, 80, 58] and(...TRUNCATED) | countdown | "To solve the problem, we need to use the numbers [44, 5, 80, 58] and apply basic arithmetic operati(...TRUNCATED) | 5 | 0 | "<answer>\nStep 1: 80 + 58 = 138\nStep 2: 138 - 44 = 94\nStep 3: 94 * 3 = 282\nStep 4: 282 + 76 = 35(...TRUNCATED) | "Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED) | 0 | false | Line uses unavailable numbers: Step 3: 94 * 3 = 282 | [["<answer>\nStep 1: 80 + 58 = 138\nStep 2: 138 - 44 = 94\nStep 3: 94 * 3 = 282\nStep 4: 282 + 76 = (...TRUNCATED) | [
[
false,
false,
false
],
[
false
],
[
false
],
[
false
],
[
false,
false,
false,
false
],
[
false,
false,
false
]
] | [["Line uses unavailable numbers: Step 3: 94 * 3 = 282","Line uses unavailable numbers: Step 3: 107 (...TRUNCATED) | [
[
"",
"",
""
],
[
""
],
[
""
],
[
""
],
[
"",
"",
"",
""
],
[
"",
"",
""
]
] | ["To solve the problem, we need to use the numbers [44, 5, 80, 58] and apply basic arithmetic operat(...TRUNCATED) | ["<answer>\nStep 1: 80 - 58 = 22\nStep 2: 22 * 15 = 330\nStep 3: 330 + 28 = 358","<answer>\nStep 1: (...TRUNCATED) | [
false,
false,
false,
false,
false,
false
] | ["Line uses unavailable numbers: Step 2: 22 * 15 = 330","Line uses unavailable numbers: Step 3: 356 (...TRUNCATED) | [{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: <answer>\nStep 1: 80 - 58 =(...TRUNCATED) | ||
6 | "{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED) | 110 | "{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED) | 1 | [true] | samples_countdown4arg_2025-06-21T08-27-35.766260.jsonl | "[{\"budget_forced_chunks\": [\"Step 1: We start with the number 81. Let's try dividing it by 37 fro(...TRUNCATED) | countdown | "Step 1: We start with the number 81. Let's try dividing it by 37 from our list.\n81 / 37 = 2.243243(...TRUNCATED) | 6 | 0 | <answer>
Step 1: 29 + 81 = 110 | "Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED) | 0 | true | [["<answer>\nStep 1: 29 + 81 = 110"],["<answer>\nStep 1: 81 + 29 = 110","<answer>\nStep 1: 81 + 37 =(...TRUNCATED) | [[true],[true,false,false,true],[false,true,true],[true],[true,true],[true,true,true,true,true,true,(...TRUNCATED) | [[""],["","Incorrect final answer","Incorrect final answer",""],["Incorrect final answer","",""],[""(...TRUNCATED) | [[""],["","","",""],["","",""],[""],["",""],["","","","","","","","","","","","","","","","","","","(...TRUNCATED) | ["Step 1: We start with the number 81. Let's try dividing it by 37 from our list.\n81 / 37 = 2.24324(...TRUNCATED) | ["<answer>\nStep 1: 29 + 81 = 110","<answer>\nStep 1: 81 + 29 = 110","<answer>\nStep 1: 81 + 29 = 11(...TRUNCATED) | [
true,
true,
true,
true,
true,
true
] | [
"",
"",
"",
"",
"",
""
] | [{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: <answer>\nStep 1: 29 + 81 =(...TRUNCATED) | |||
7 | "{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED) | 896 | "{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED) | 0 | [false] | samples_countdown4arg_2025-06-21T08-27-35.766260.jsonl | "[{\"budget_forced_chunks\": [\"To solve the problem, we need to use the numbers [65, 56, 37, 12] an(...TRUNCATED) | countdown | "To solve the problem, we need to use the numbers [65, 56, 37, 12] and apply basic arithmetic operat(...TRUNCATED) | 7 | 0 | <answer>
Step 1: 65 + 37 = 102
Step 2: 102 + 56 = 158 | "Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED) | 0 | false | Incorrect final answer | [["<answer>\nStep 1: 65 + 37 = 102\nStep 2: 102 + 56 = 158","<answer>\nStep 1: 65 + 56 = 121\nStep 2(...TRUNCATED) | [
[
false,
false,
false,
false
]
] | [["Incorrect final answer","Incorrect arithmetic in line: Step 3: 84 * 12 = 968","Incorrect final an(...TRUNCATED) | [
[
"",
"",
"",
""
]
] | ["To solve the problem, we need to use the numbers [65, 56, 37, 12] and apply basic arithmetic opera(...TRUNCATED) | [
"<answer>\nStep 1: 65 + 56 = 121\nStep 2: 121 - 37 = 84\nStep 3: 84 * 12 = 968"
] | [
false
] | [
"Incorrect arithmetic in line: Step 3: 84 * 12 = 968"
] | [{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: <answer>\nStep 1: 65 + 56 =(...TRUNCATED) | ||
8 | "{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED) | 189 | "{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED) | 0 | [false] | samples_countdown4arg_2025-06-21T08-27-35.766260.jsonl | "[{\"budget_forced_chunks\": [\"To solve the problem, we need to use the numbers [4, 13, 64, 60] and(...TRUNCATED) | countdown | "To solve the problem, we need to use the numbers [4, 13, 64, 60] and apply basic arithmetic operati(...TRUNCATED) | 8 | 0 | <answer>
Step 1: 64 - 60 = 4
Step 2: 4 * 4 = 16 | "Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED) | 0 | false | Incorrect final answer | [["<answer>\nStep 1: 64 - 60 = 4\nStep 2: 4 * 4 = 16","<answer>\nStep 1: 64 + 13 = 77\nStep 2: 77 * (...TRUNCATED) | [
[
false,
false,
false,
false,
true
],
[
false,
false,
false,
false
],
[
false,
false
]
] | [["Incorrect final answer","Incorrect final answer","Incorrect final answer","Incorrect final answer(...TRUNCATED) | [
[
"",
"",
"",
"",
""
],
[
"",
"",
"",
""
],
[
"",
""
]
] | ["To solve the problem, we need to use the numbers [4, 13, 64, 60] and apply basic arithmetic operat(...TRUNCATED) | ["<answer>\nStep 1: 60 * 4 = 240\nStep 2: 240 + 13 = 253\nStep 3: 253 - 64 = 189","<answer>\nStep 1:(...TRUNCATED) | [
true,
false,
false
] | [
"",
"Incorrect arithmetic in line: Step 3: 128 + 60 = 189",
"Incorrect final answer"
] | [{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: <answer>\nStep 1: 60 * 4 = (...TRUNCATED) | ||
9 | "{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED) | 298 | "{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED) | 0 | [false] | samples_countdown4arg_2025-06-21T08-27-35.766260.jsonl | "[{\"budget_forced_chunks\": [\"To solve the problem, we need to use the numbers [62, 56, 32, 55] an(...TRUNCATED) | countdown | "To solve the problem, we need to use the numbers [62, 56, 32, 55] and apply basic arithmetic operat(...TRUNCATED) | 9 | 0 | <answer>
Step 1: 62 - 56 = 6
Step 2: 6 * 55 = 330 | "Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED) | 0 | false | Incorrect final answer | [["<answer>\nStep 1: 62 - 56 = 6\nStep 2: 6 * 55 = 330","<answer>\nStep 1: 62 - 56 = 6\nStep 2: 6 * (...TRUNCATED) | [
[
false,
false
]
] | [
[
"Incorrect final answer",
"Incorrect final answer"
]
] | [
[
"",
""
]
] | ["To solve the problem, we need to use the numbers [62, 56, 32, 55] and apply basic arithmetic opera(...TRUNCATED) | [
"<answer>\nStep 1: 62 - 56 = 6\nStep 2: 6 * 55 = 330"
] | [
false
] | [
"Incorrect final answer"
] | [{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: <answer>\nStep 1: 62 - 56 =(...TRUNCATED) |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 7