Datasets:
Modalities:
Text
Formats:
parquet
Size:
< 1K
Tags:
degen_test_1_countdown
budget-32k
iterative
hosted_vllm-Qwen-Qwen3-4B-Thinking-2507<api_base>http:--10.32.37.15:10080-v1
License:
question stringlengths 152 158 | metadata stringlengths 160 172 | task_source stringclasses 1
value | formatted_prompt listlengths 2 2 | responses_by_sample listlengths 1 1 | tokens_by_sample listlengths 1 1 | num_rounds_by_sample listlengths 1 1 | continuation_prompts_by_sample listlengths 1 1 | continuation_text_by_sample listlengths 1 1 | strategy_type stringclasses 1
value | termination_reason_by_sample listlengths 1 1 | correct_round_by_sample listlengths 1 1 | smart_termination_enabled bool 1
class | answers_by_sample listlengths 1 1 | evals_by_sample listlengths 1 1 | eval_metadata_by_sample listlengths 1 1 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Using ALL of the numbers 12, 4, 7, 1, 2, 5, 21, 88, create an expression that equals 109. You must use each number exactly once. You may use +, -, *, /. | {"numbers": [12, 4, 7, 1, 2, 5, 21, 88], "target": 109, "operators_used": ["/", "+", "/", "/", "/", "*", "+"], "expression": "12 / 4 + 7 / 1 / 2 / 5 * 21 + 88"} | countdown | [
{
"content": "You are a helpful assistant that solves math problems by reasoning step-by-step. Show your work clearly and provide complete solutions. You MUST use ALL of the given numbers exactly once in your solution. When you have a final answer, wrap it in <answer></answer> tags.",
"role": "system"
},
... | [
[
"<think>\nOkay, let's see. I need to use all the numbers 12, 4, 7, 1, 2, 5, 21, 88 exactly once with +, -, *, / to make 109. Hmm, that's a bit challenging. Let me start by listing out all the numbers to keep track: 12, 4, 7, 1, 2, 5, 21, 88. Eight numbers total.\n\nFirst thought: Maybe start by looking at the... | [
33506
] | [
25
] | [
[
"Continue exploring alternative solution strategies.",
"Continue exploring alternative solution strategies.",
"Continue exploring alternative solution strategies.",
"Continue exploring alternative solution strategies.",
"Continue exploring alternative solution strategies.",
"Continue explo... | [
[
"<think>\nOkay, let's see. I need to use all the numbers 12, 4, 7, 1, 2, 5, 21, 88 exactly once with +, -, *, / to make 109. Hmm, that's a bit challenging. Let me start by listing out all the numbers to keep track: 12, 4, 7, 1, 2, 5, 21, 88. Eight numbers total.\n\nFirst thought: Maybe start by looking at the... | iterative | [
"budget_reached"
] | [
null
] | false | [
[
[
"88 + 21 + (12 - 5) * (7 - 4 - 2 - 1)"
],
[],
[
"(88 + 21) + (12 - 5) * (7 - (4 + 2 + 1))"
],
[],
[
"(88 + 21) - (12 - 5) * (7 - 4 - 2 - 1)",
"(88 + 21) - (12 - 5) * (7 - 4 - 2 - 1)"
],
[
"(88 + 21) + (5 - (12 - 7)) * (4 + 2 + 1)"
],
[],
... | [
[
[
true
],
[],
[
true
],
[],
[
true,
true
],
[
true
],
[],
[
true
],
[
true,
true
],
[],
[
true
],
[
true,
true
],
[
true
],
[
true,
true
... | [
[
[
{
"answer_block": "88 + 21 + (12 - 5) * (7 - 4 - 2 - 1)",
"error": null,
"final_answer": 109,
"is_correct": true
}
],
[],
[
{
"answer_block": "(88 + 21) + (12 - 5) * (7 - (4 + 2 + 1))",
"error": null,
"final_answer": 109,
... |
"Using ALL of the numbers 25, 69, 58, 14, 55, 24, 36, 60, create an expression that equals 176. You (...TRUNCATED) | "{\"numbers\": [25, 69, 58, 14, 55, 24, 36, 60], \"target\": 176, \"operators_used\": [\"-\", \"+\",(...TRUNCATED) | countdown | [{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED) | [["<think>\nOkay, let's try to figure out how to make 176 using all these numbers: 25, 69, 58, 14, 5(...TRUNCATED) | [
33453
] | [
17
] | [["Continue exploring alternative solution strategies.","Continue exploring alternative solution str(...TRUNCATED) | [["<think>\nOkay, let's try to figure out how to make 176 using all these numbers: 25, 69, 58, 14, 5(...TRUNCATED) | iterative | [
"budget_reached"
] | [
null
] | false | [[["(69 - 58) * (25 - 14) + 60 + 55 + 36 - 24"],["(69 - 58) * (25 - 14) + 60 + 55 + 36 - 24"],["(69 (...TRUNCATED) | [[[false],[false],[false],[],[true,true],[true],[true,true],[true],[true,true],[],[],[true],[true,tr(...TRUNCATED) | [[[{"answer_block":"(69 - 58) * (25 - 14) + 60 + 55 + 36 - 24","error":"Expression does not equal st(...TRUNCATED) |
"Using ALL of the numbers 55, 36, 6, 3, 14, 99, 17, 82, create an expression that equals 245. You mu(...TRUNCATED) | "{\"numbers\": [55, 36, 6, 3, 14, 99, 17, 82], \"target\": 245, \"operators_used\": [\"*\", \"-\", \(...TRUNCATED) | countdown | [{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED) | [["<think>\nOkay, let's see. I need to use all these numbers: 55, 36, 6, 3, 14, 99, 17, 82. Each exa(...TRUNCATED) | [
33058
] | [
13
] | [["Continue exploring alternative solution strategies.","Continue exploring alternative solution str(...TRUNCATED) | [["<think>\nOkay, let's see. I need to use all these numbers: 55, 36, 6, 3, 14, 99, 17, 82. Each exa(...TRUNCATED) | iterative | [
"budget_reached"
] | [
null
] | false | [[["(82 * 3) - ((99 - 55 - 36) / (17 - 14 - 6))"],["( (99 - 55 - (36 / 6) - 3) * (14 / (6 / 3)) ) * (...TRUNCATED) | [[[false],[false],[false,false],[],[false],[false,false,false,false],[false],[],[false,false],[false(...TRUNCATED) | [[[{"answer_block":"(82 * 3) - ((99 - 55 - 36) / (17 - 14 - 6))","error":"Expression does not equal (...TRUNCATED) |
"Using ALL of the numbers 87, 87, 29, 2, 19, 4, 1, 1, create an expression that equals 281. You must(...TRUNCATED) | "{\"numbers\": [87, 87, 29, 2, 19, 4, 1, 1], \"target\": 281, \"operators_used\": [\"/\", \"+\", \"/(...TRUNCATED) | countdown | [{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED) | [["","","<think>\nOkay, let's try to figure out how to make 281 using all the numbers 87, 87, 29, 2,(...TRUNCATED) | [
32834
] | [
24
] | [["Continue exploring alternative solution strategies.","Continue exploring alternative solution str(...TRUNCATED) | [["","","<think>\nOkay, let's try to figure out how to make 281 using all the numbers 87, 87, 29, 2,(...TRUNCATED) | iterative | [
"budget_reached"
] | [
null
] | false | [[[],[],["87 + 87 + 29 + 19 * 4 + 2 + 1 - 1"],[],[],["87 + 87 + 29 + 19 * 4 + 2 + 1 - 1"],[],[],[],[(...TRUNCATED) | [[[],[],[true],[],[],[true],[],[],[],[],[true],[],[true,true],[true],[true,true],[true,true],[true],(...TRUNCATED) | [[[],[],[{"answer_block":"87 + 87 + 29 + 19 * 4 + 2 + 1 - 1","error":null,"final_answer":281.0,"is_c(...TRUNCATED) |
"Using ALL of the numbers 56, 63, 7, 50, 44, 1, 87, 52, create an expression that equals 132. You mu(...TRUNCATED) | "{\"numbers\": [56, 63, 7, 50, 44, 1, 87, 52], \"target\": 132, \"operators_used\": [\"-\", \"/\", \(...TRUNCATED) | countdown | [{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED) | [["<think>\nOkay, let's see. I need to make an expression that equals 132 using all the numbers 56, (...TRUNCATED) | [
33074
] | [
17
] | [["Continue exploring alternative solution strategies.","Continue exploring alternative solution str(...TRUNCATED) | [["<think>\nOkay, let's see. I need to make an expression that equals 132 using all the numbers 56, (...TRUNCATED) | iterative | [
"budget_reached"
] | [
null
] | false | [[["87 + 52 - 7 + 50 - 44 - 63 + 56 + 1"],[],["(87 + 52 - 7) - (63 - 56) + (50 - 44) + 1"],[],["(87 (...TRUNCATED) | [[[true],[],[true],[],[true,true],[true],[true],[],[],[true,true],[true],[],[true,true],[],[false,fa(...TRUNCATED) | [[[{"answer_block":"87 + 52 - 7 + 50 - 44 - 63 + 56 + 1","error":null,"final_answer":132.0,"is_corre(...TRUNCATED) |
"Using ALL of the numbers 7, 1, 49, 7, 28, 59, 3, 44, create an expression that equals 521. You must(...TRUNCATED) | "{\"numbers\": [7, 1, 49, 7, 28, 59, 3, 44], \"target\": 521, \"operators_used\": [\"/\", \"*\", \"/(...TRUNCATED) | countdown | [{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED) | [["<think>\nOkay, let's try to solve this problem. We need to use all the numbers 7, 1, 49, 7, 28, 5(...TRUNCATED) | [
32994
] | [
24
] | [["Continue exploring alternative solution strategies.","Continue exploring alternative solution str(...TRUNCATED) | [["<think>\nOkay, let's try to solve this problem. We need to use all the numbers 7, 1, 49, 7, 28, 5(...TRUNCATED) | iterative | [
"budget_reached"
] | [
null
] | false | [[["49 - (7 / 7) + 59 * ((44 - 28) / (3 - 1)) + 1"],["49 - (7 / 7) + 59 * ((44 - 28) / (3 - 1)) + 1"(...TRUNCATED) | [[[false],[false],[false],[],[],[false,false],[false],[false,false],[false],[],[],[],[],[],[false,fa(...TRUNCATED) | [[[{"answer_block":"49 - (7 / 7) + 59 * ((44 - 28) / (3 - 1)) + 1","error":"Expression uses an unava(...TRUNCATED) |
"Using ALL of the numbers 97, 4, 93, 26, 3, 24, 20, 31, create an expression that equals 620. You mu(...TRUNCATED) | "{\"numbers\": [97, 4, 93, 26, 3, 24, 20, 31], \"target\": 620, \"operators_used\": [\"-\", \"/\", \(...TRUNCATED) | countdown | [{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED) | [["<think>\nOkay, let's try to figure out how to make 620 using all these numbers: 97, 4, 93, 26, 3,(...TRUNCATED) | [
36309
] | [
1
] | [
[]
] | [["<think>\nOkay, let's try to figure out how to make 620 using all these numbers: 97, 4, 93, 26, 3,(...TRUNCATED) | iterative | [
"budget_reached"
] | [
null
] | false | [
[
[
"26 * 24 - (97 - 93) + (4 - 3) * (20 - 31)"
]
]
] | [
[
[
false
]
]
] | [[[{"answer_block":"26 * 24 - (97 - 93) + (4 - 3) * (20 - 31)","error":"Expression does not equal st(...TRUNCATED) |
"Using ALL of the numbers 45, 69, 55, 40, 1, 9, 8, 83, create an expression that equals 913. You mus(...TRUNCATED) | "{\"numbers\": [45, 69, 55, 40, 1, 9, 8, 83], \"target\": 913, \"operators_used\": [\"*\", \"+\", \"(...TRUNCATED) | countdown | [{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED) | [["<think>\nOkay, let's try to solve this problem. We need to use all the numbers 45, 69, 55, 40, 1,(...TRUNCATED) | [
33037
] | [
33
] | [["Continue exploring alternative solution strategies.","Continue exploring alternative solution str(...TRUNCATED) | [["<think>\nOkay, let's try to solve this problem. We need to use all the numbers 45, 69, 55, 40, 1,(...TRUNCATED) | iterative | [
"budget_reached"
] | [
null
] | false | [[["83 * (69 - 55 - 45 + 40 + 9 - 8 + 1)"],[],["83 * (69 - 55 - 45 + 40 + 9 - 8 + 1)"],[],[],[],[],[(...TRUNCATED) | [[[true],[],[true],[],[],[],[],[],[true,true],[],[],[true],[true,true],[],[],[true],[true,true],[],[(...TRUNCATED) | [[[{"answer_block":"83 * (69 - 55 - 45 + 40 + 9 - 8 + 1)","error":null,"final_answer":913.0,"is_corr(...TRUNCATED) |
"Using ALL of the numbers 72, 3, 67, 1, 43, 1, 93, 53, create an expression that equals 145. You mus(...TRUNCATED) | "{\"numbers\": [72, 3, 67, 1, 43, 1, 93, 53], \"target\": 145, \"operators_used\": [\"/\", \"-\", \"(...TRUNCATED) | countdown | [{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED) | [["<think>\nOkay, let's see. I need to use all the numbers 72, 3, 67, 1, 43, 1, 93, 53 to make 145. (...TRUNCATED) | [
35433
] | [
28
] | [["Continue exploring alternative solution strategies.","Continue exploring alternative solution str(...TRUNCATED) | [["<think>\nOkay, let's see. I need to use all the numbers 72, 3, 67, 1, 43, 1, 93, 53 to make 145. (...TRUNCATED) | iterative | [
"budget_reached"
] | [
null
] | false | [[["93 + 53 - (72 / 3 - (67 - 43) + 1 * 1)","93 + 53 - (72 / 3 - (67 - 43) + 1 * 1)"],[],[],[],["93 (...TRUNCATED) | [[[true,true],[],[],[],[true],[],[true,true],[true],[],[],[],[true,true],[true],[],[],[],[],[true,tr(...TRUNCATED) | [[[{"answer_block":"93 + 53 - (72 / 3 - (67 - 43) + 1 * 1)","error":null,"final_answer":145.0,"is_co(...TRUNCATED) |
"Using ALL of the numbers 13, 1, 13, 68, 2, 2, 93, 62, create an expression that equals 102. You mus(...TRUNCATED) | "{\"numbers\": [13, 1, 13, 68, 2, 2, 93, 62], \"target\": 102, \"operators_used\": [\"/\", \"-\", \"(...TRUNCATED) | countdown | [{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED) | [["","","","","","","","","<think>\nOkay, let's try to figure out how to make 102 using all the numb(...TRUNCATED) | [
35975
] | [
9
] | [["Continue exploring alternative solution strategies.","Continue exploring alternative solution str(...TRUNCATED) | [["","","","","","","","","<think>\nOkay, let's try to figure out how to make 102 using all the numb(...TRUNCATED) | iterative | [
"budget_reached"
] | [
null
] | false | [[[],[],[],[],[],[],[],[],["(93 - (13 + 13 + 2)) * 2 + (68 - 62) - 1","(93 * 2) - 68 - 13 - 2 - 1 - (...TRUNCATED) | [
[
[],
[],
[],
[],
[],
[],
[],
[],
[
false,
false,
false,
true
]
]
] | [[[],[],[],[],[],[],[],[],[{"answer_block":"(93 - (13 + 13 + 2)) * 2 + (68 - 62) - 1","error":"Expre(...TRUNCATED) |
End of preview. Expand in Data Studio
EAS-Qwen3-4B-Thinking-2507-cd8arg-iterative
Countdown reasoning with iterative strategy to 32768 tokens
Dataset Info
- Rows: 100
- Columns: 16
Columns
| Column | Type | Description |
|---|---|---|
| question | Value('string') | The countdown problem statement |
| metadata | Value('string') | JSON with target number, available numbers, and solution |
| task_source | Value('string') | Task type identifier (countdown) |
| formatted_prompt | List({'content': Value('string'), 'role': Value('string')}) | Initial prompt messages sent to the model |
| responses_by_sample | List(List(Value('string'))) | Full model response [sample_idx][round_idx] = response string |
| tokens_by_sample | List(Value('int64')) | Total token count for each sample (based on continuation_text) |
| num_rounds_by_sample | List(Value('int64')) | Number of continuation rounds for each sample |
| continuation_prompts_by_sample | List(List(Value('string'))) | Continuation prompts used [sample_idx][round_idx] = prompt string |
| continuation_text_by_sample | List(List(Value('string'))) | Truncated text used for continuation [sample_idx][round_idx]. For budget_forcing: truncated at first tag. For other strategies: same as responses_by_sample. |
| strategy_type | Value('string') | Prompting strategy: 'iterative', 'budget_forcing', or 'random_noise' |
| termination_reason_by_sample | List(Value('string')) | Why each sample terminated: 'max_rounds_reached', 'budget_reached', or 'answer_correct' |
| correct_round_by_sample | List(Value('null')) | Round number where correct answer was first found (None if never correct) |
| smart_termination_enabled | Value('bool') | Whether smart termination was enabled for this run |
| answers_by_sample | List(List(List(Value('string')))) | Extracted answer spans [sample][round][answer_idx] |
| evals_by_sample | List(List(List(Value('bool')))) | Correctness evaluations [sample][round][answer_idx] |
| eval_metadata_by_sample | List(List(List({'answer_block': Value('string'), 'error': Value('string'), 'final_answer': Value('float64'), 'is_correct': Value('bool')}))) | Evaluation details [sample][round][answer_idx] |
Generation Parameters
{
"script_name": "stage_01_generate_reasoning.py",
"model": "hosted_vllm/Qwen/Qwen3-4B-Thinking-2507<api_base>http://10.32.37.15:10080/v1",
"hyperparameters": {
"temperature": 0.7,
"max_tokens_per_round": 32768,
"target_total_tokens": 32768,
"samples": 1,
"strategy": "iterative",
"max_rounds": null
},
"input_datasets": [],
"description": "Countdown reasoning with iterative strategy to 32768 tokens",
"experiment": "degen_test_1_countdown",
"strategy": "iterative",
"arg_count": 8,
"seed": 42,
"smart_termination": false,
"max_rounds": null,
"status": "completed",
"completed_at": "2025-12-22T10:43:30.349936"
}
Experiment Documentation
For complete experiment details, see https://github.com/TAUR-Lab/Reasoning-Horizons/tree/main/experiments/degen_test_1_countdown
Usage
from datasets import load_dataset
dataset = load_dataset("reasoning-degeneration-dev/EAS-Qwen3-4B-Thinking-2507-cd8arg-iterative", split="train")
print(f"Loaded {len(dataset)} rows")
This dataset is tracked in reasoning-degeneration-dev/PROJECT-MANIFEST
- Downloads last month
- 8