Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringclasses
10 values
metadata
stringclasses
10 values
task_source
stringclasses
1 value
formatted_prompt
listlengths
2
2
response
listlengths
1
1
formatted_prompt__metadata
listlengths
1
1
response__metadata
listlengths
1
1
response__extractions
listlengths
1
1
response__extractions_metadata
listlengths
1
1
eval_correct
listlengths
1
1
eval_correct__metadata
listlengths
1
1
_judge_prompt__metadata
listlengths
1
1
_judge_response__metadata
listlengths
1
1
strategy_compliance
int64
1
4
compliance_reasoning
stringclasses
10 values
compliance_elements_followed
listlengths
0
7
compliance_elements_missed
listlengths
1
8
"Using ALL of the numbers 28, 98, 44, 14, 69, 49, 7, 46, create an expression that equals 303. You m(...TRUNCATED)
"{\"numbers\": [28, 98, 44, 14, 69, 49, 7, 46], \"target\": 303, \"operators_used\": [\"*\", \"*\", (...TRUNCATED)
countdown
[{"content":"You are a math problem solver. Solve the given arithmetic problem step by step. Show yo(...TRUNCATED)
["Okay, let's see. I need to use all the numbers 28, 98, 44, 14, 69, 49, 7, 46 to make 303. Hmm, tha(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED)
[{"cost":0.04927695,"finish_reason":"length","input_tokens":833,"model":"together_ai/Qwen/Qwen3-Next(...TRUNCATED)
[ [] ]
[ [] ]
[ [] ]
[ [] ]
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.004401749999999999,"finish_reason":"stop","input_tokens":28705,"model":"gpt-4o-mini-2024-(...TRUNCATED)
2
"The model begins by listing the available numbers and the target, which aligns with the inventory s(...TRUNCATED)
[ "Lists all available numbers and target at the start (INVENTORY step)" ]
["Picks pairs of numbers and tries operations systematically (BRANCH step)","Tracks the available nu(...TRUNCATED)
"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 math problem solver. Solve the given arithmetic problem step by step. Show yo(...TRUNCATED)
["Okay, let's tackle this problem. We need to use all the numbers 25, 69, 58, 14, 55, 24, 36, 60 to (...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED)
[{"cost":0.049277100000000004,"finish_reason":"length","input_tokens":834,"model":"together_ai/Qwen/(...TRUNCATED)
[ [] ]
[ [] ]
[ [] ]
[ [] ]
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.00409305,"finish_reason":"stop","input_tokens":26411,"model":"gpt-4o-mini-2024-07-18","ou(...TRUNCATED)
2
"The model begins by acknowledging the strategy and listing the available numbers and target, which (...TRUNCATED)
[ "Lists all available numbers and target at the start (INVENTORY step)" ]
["Picks pairs of numbers and tries operations systematically (BRANCH step)","Tracks the available nu(...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 math problem solver. Solve the given arithmetic problem step by step. Show yo(...TRUNCATED)
["<think>\nOkay, let's see. I need to use all the numbers 55, 36, 6, 3, 14, 99, 17, 82 to make 245. (...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED)
[{"cost":0.0097188,"finish_reason":"stop","input_tokens":832,"model":"together_ai/Qwen/Qwen3-Next-80(...TRUNCATED)
[["tags.\n\nBut the problem says \"the answer should be a single arithmetic expression using the giv(...TRUNCATED)
[ [ { "end_index": 14687, "end_phrase": "</answer>", "start_index": 14067, "start_phrase": "<answer>" } ] ]
[ [ false ] ]
[[{"answer_block":"tags.\n\nBut the problem says \"the answer should be a single arithmetic expressi(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.0010739999999999999,"finish_reason":"stop","input_tokens":6288,"model":"gpt-4o-mini-2024-(...TRUNCATED)
3
"The model demonstrates some understanding of the systematic tree search strategy, particularly in l(...TRUNCATED)
["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...TRUNCATED)
["Uses explicit tree structure (branches, levels, indentation, or labeling)","Explicitly marks dead (...TRUNCATED)
"Using ALL of the numbers 87, 69, 43, 4, 55, 34, 23, 2, create an expression that equals 874. You mu(...TRUNCATED)
"{\"numbers\": [87, 69, 43, 4, 55, 34, 23, 2], \"target\": 874, \"operators_used\": [\"*\", \"+\", \(...TRUNCATED)
countdown
[{"content":"You are a math problem solver. Solve the given arithmetic problem step by step. Show yo(...TRUNCATED)
["<think>\nOkay, let's tackle this problem. We need to use all the numbers 87, 69, 43, 4, 55, 34, 23(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED)
[{"cost":0.047647800000000004,"finish_reason":"stop","input_tokens":832,"model":"together_ai/Qwen/Qw(...TRUNCATED)
[["(55 - 34 - (4 / 2)) * 23 + (87 - 69 - 43)","(55 - (34 / 2)) * 23 + (87 - 69 - 43 + 4)","(87 * (69(...TRUNCATED)
[[{"end_index":59286,"end_phrase":"</answer>","start_index":59228,"start_phrase":"<answer>"},{"end_i(...TRUNCATED)
[ [ false, false, false, false, false, false, false ] ]
[[{"answer_block":"(55 - 34 - (4 / 2)) * 23 + (87 - 69 - 43)","error":"Could not evaluate expression(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.00408195,"finish_reason":"stop","input_tokens":26357,"model":"gpt-4o-mini-2024-07-18","ou(...TRUNCATED)
1
"The model completely disregards the prescribed strategy and instead engages in a lengthy, unstructu(...TRUNCATED)
[]
["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...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 math problem solver. Solve the given arithmetic problem step by step. Show yo(...TRUNCATED)
["<think>\nOkay, let's see. I need to use all the numbers 56, 63, 7, 50, 44, 1, 87, 52 to make 132. (...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED)
[{"cost":0.0141933,"finish_reason":"stop","input_tokens":832,"model":"together_ai/Qwen/Qwen3-Next-80(...TRUNCATED)
[ [ "((87 + 56) - (63 - 52)) * ((50 - 44) / (7 - 1))" ] ]
[ [ { "end_index": 20704, "end_phrase": "</answer>", "start_index": 20640, "start_phrase": "<answer>" } ] ]
[ [ false ] ]
[[{"answer_block":"((87 + 56) - (63 - 52)) * ((50 - 44) / (7 - 1))","error":"Could not evaluate expr(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.0014367,"finish_reason":"stop","input_tokens":8690,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED)
4
"The model demonstrates a strong adherence to the systematic tree search strategy, including a clear(...TRUNCATED)
["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...TRUNCATED)
[ "Avoids heuristic reasoning (no 'close to target', 'approximately', estimation)" ]
"Using ALL of the numbers 32, 32, 36, 58, 2, 97, 60, 11, create an expression that equals 409. You m(...TRUNCATED)
"{\"numbers\": [32, 32, 36, 58, 2, 97, 60, 11], \"target\": 409, \"operators_used\": [\"/\", \"*\", (...TRUNCATED)
countdown
[{"content":"You are a math problem solver. Solve the given arithmetic problem step by step. Show yo(...TRUNCATED)
["<think>\nOkay, let's see. I need to use all the numbers 32, 32, 36, 58, 2, 97, 60, 11 to make 409.(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED)
[{"cost":0.011853450000000001,"finish_reason":"stop","input_tokens":833,"model":"together_ai/Qwen/Qw(...TRUNCATED)
[ [ "((97 * (36 - 32)) + (32 - 11)) * (60 / (58 + 2))" ] ]
[ [ { "end_index": 18539, "end_phrase": "</answer>", "start_index": 18474, "start_phrase": "<answer>" } ] ]
[ [ false ] ]
[[{"answer_block":"((97 * (36 - 32)) + (32 - 11)) * (60 / (58 + 2))","error":"Could not evaluate exp(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.0012541499999999999,"finish_reason":"stop","input_tokens":7525,"model":"gpt-4o-mini-2024-(...TRUNCATED)
2
"The model acknowledges the strategy and attempts to follow it but quickly reverts to a more ad-hoc (...TRUNCATED)
[ "Lists all available numbers and target at the start (INVENTORY step)" ]
["Picks pairs of numbers and tries operations systematically (BRANCH step)","Tracks the available nu(...TRUNCATED)
"Using ALL of the numbers 38, 30, 47, 23, 39, 2, 91, 1, create an expression that equals 785. You mu(...TRUNCATED)
"{\"numbers\": [38, 30, 47, 23, 39, 2, 91, 1], \"target\": 785, \"operators_used\": [\"-\", \"*\", \(...TRUNCATED)
countdown
[{"content":"You are a math problem solver. Solve the given arithmetic problem step by step. Show yo(...TRUNCATED)
["<think>\nOkay, let's see. I need to use all the numbers 38, 30, 47, 23, 39, 2, 91, 1 to make 785. (...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED)
[{"cost":0.008791799999999999,"finish_reason":"stop","input_tokens":832,"model":"together_ai/Qwen/Qw(...TRUNCATED)
[ [ "91 * (38 - 30) + 47 + 23 - 39 / (2 + 1)" ] ]
[ [ { "end_index": 12828, "end_phrase": "</answer>", "start_index": 12772, "start_phrase": "<answer>" } ] ]
[ [ false ] ]
[[{"answer_block":"91 * (38 - 30) + 47 + 23 - 39 / (2 + 1)","error":"Could not evaluate expression",(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.00100005,"finish_reason":"stop","input_tokens":5783,"model":"gpt-4o-mini-2024-07-18","out(...TRUNCATED)
4
"The model demonstrates a strong adherence to the systematic tree search strategy, including a clear(...TRUNCATED)
["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...TRUNCATED)
[ "Avoids heuristic reasoning (no 'close to target', 'approximately', estimation)" ]
"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 math problem solver. Solve the given arithmetic problem step by step. Show yo(...TRUNCATED)
["<think>\nOkay, let's try to solve this problem. We need to use all the numbers 13, 1, 13, 68, 2, 2(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED)
[{"cost":0.01170765,"finish_reason":"stop","input_tokens":831,"model":"together_ai/Qwen/Qwen3-Next-8(...TRUNCATED)
[ [ "68 * 2 - (93 - 62 + 13 / 13 + 2) * 1" ] ]
[ [ { "end_index": 17257, "end_phrase": "</answer>", "start_index": 17204, "start_phrase": "<answer>" } ] ]
[ [ false ] ]
[[{"answer_block":"68 * 2 - (93 - 62 + 13 / 13 + 2) * 1","error":"Could not evaluate expression","fi(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.0012444,"finish_reason":"stop","input_tokens":7596,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED)
2
"The model begins by listing the available numbers and the target, which aligns with the inventory s(...TRUNCATED)
[ "Lists all available numbers and target at the start (INVENTORY step)" ]
["Picks pairs of numbers and tries operations systematically (BRANCH step)","Tracks the available nu(...TRUNCATED)
"Using ALL of the numbers 87, 1, 21, 9, 57, 45, 6, 17, create an expression that equals 113. You mus(...TRUNCATED)
"{\"numbers\": [87, 1, 21, 9, 57, 45, 6, 17], \"target\": 113, \"operators_used\": [\"/\", \"*\", \"(...TRUNCATED)
countdown
[{"content":"You are a math problem solver. Solve the given arithmetic problem step by step. Show yo(...TRUNCATED)
["Okay, let's tackle this problem step by step. The goal is to use all the numbers 87, 1, 21, 9, 57,(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED)
[{"cost":0.04927665,"finish_reason":"length","input_tokens":831,"model":"together_ai/Qwen/Qwen3-Next(...TRUNCATED)
[ [ "87 + 17 + 57 - 45 - 21 + 9 - 6 - 1 = 113", "87 + 17 + 57 - 45 - 21 + 9 - 6 - 1 = 113" ] ]
[[{"end_index":59592,"end_phrase":"</answer>","start_index":59535,"start_phrase":"<answer>"},{"end_i(...TRUNCATED)
[ [ false, false ] ]
[[{"answer_block":"87 + 17 + 57 - 45 - 21 + 9 - 6 - 1 = 113","error":"Could not evaluate expression"(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.0042165,"finish_reason":"stop","input_tokens":27298,"model":"gpt-4o-mini-2024-07-18","out(...TRUNCATED)
2
"The model acknowledges the strategy at the beginning but quickly reverts to a more ad-hoc reasoning(...TRUNCATED)
[ "Lists all available numbers and target at the start (INVENTORY step)" ]
["Picks pairs of numbers and tries operations systematically (BRANCH step)","Tracks the available nu(...TRUNCATED)
"Using ALL of the numbers 60, 90, 39, 30, 53, 15, 18, 6, create an expression that equals 239. You m(...TRUNCATED)
"{\"numbers\": [60, 90, 39, 30, 53, 15, 18, 6], \"target\": 239, \"operators_used\": [\"+\", \"*\", (...TRUNCATED)
countdown
[{"content":"You are a math problem solver. Solve the given arithmetic problem step by step. Show yo(...TRUNCATED)
["<think>\nOkay, let's tackle this problem. We need to use all the numbers 60, 90, 39, 30, 53, 15, 1(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED)
[{"cost":0.008427450000000001,"finish_reason":"stop","input_tokens":833,"model":"together_ai/Qwen/Qw(...TRUNCATED)
[ [ "(90 + 60 + 53 + 6 + 39) - (18 / (30 / 15))" ] ]
[ [ { "end_index": 12335, "end_phrase": "</answer>", "start_index": 12276, "start_phrase": "<answer>" } ] ]
[ [ false ] ]
[[{"answer_block":"(90 + 60 + 53 + 6 + 39) - (18 / (30 / 15))","error":"Could not evaluate expressio(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.0009454499999999999,"finish_reason":"stop","input_tokens":5479,"model":"gpt-4o-mini-2024-(...TRUNCATED)
2
"The model acknowledges the strategy and attempts to follow it but quickly reverts to a more ad-hoc (...TRUNCATED)
[ "Lists all available numbers and target at the start (INVENTORY step)" ]
["Picks pairs of numbers and tries operations systematically (BRANCH step)","Tracks the available nu(...TRUNCATED)

t1-strategy-countdown-treesearch-together_ai-qwen-qwen3-next-80b-a3b-thin-8d79a62b

Strategy compliance evaluation on countdown arithmetic — tree-search variant.

Model was instructed to use a systematic tree search with explicit backtracking. Compliance is scored by an LLM judge (1-5 Likert).

Results

Metric Value
pass@1 0.0000
Strategy compliance (mean) 2.40
Strategy compliance (min) 1
Strategy compliance (max) 4
Total problems 10

Compliance Distribution

Score Count Meaning
1 1 Non-compliant
2 6 Minimal
3 1 Partial
4 2 Mostly compliant
5 0 Fully compliant

Details

Parameter Value
Model together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking
Thinking True
Temperature 0.7
Max tokens 32768
Judge model openai/gpt-4o-mini
Num examples 10
Num args 8
Variant tree-search

Usage

from datasets import load_dataset
ds = load_dataset("reasoning-degeneration-dev/t1-strategy-countdown-treesearch-together_ai-qwen-qwen3-next-80b-a3b-thin-8d79a62b", split="train")
scores = ds["strategy_compliance"]
print(f"Mean compliance: {sum(scores) / len(scores):.2f}")

Tracked in reasoning-degeneration-dev/PROJECT-MANIFEST

Downloads last month
5