question string | metadata string | task_source string | formatted_prompt list | response list | formatted_prompt__metadata list | response__metadata list | response__extractions list | response__extractions_metadata list | eval_correct list | eval_correct__metadata list | _judge_prompt__metadata list | _judge_response__metadata list | strategy_compliance int64 | compliance_reasoning string | compliance_elements_followed list | compliance_elements_missed list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
"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) | ["<think>\nOkay, let's see. I need to use all these numbers: 28, 98, 44, 14, 69, 49, 7, 46 to make 3(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.0246138,"finish_reason":"stop","input_tokens":172,"model":"together_ai/Qwen/Qwen3-Next-80(...TRUNCATED) | [
[
"44 * 7 - (98 / 14 - (69 - 49) + (46 - 28))"
]
] | [
[
{
"end_index": 35928,
"end_phrase": "</answer>",
"start_index": 35869,
"start_phrase": "<answer>"
}
]
] | [
[
false
]
] | [[{"answer_block":"44 * 7 - (98 / 14 - (69 - 49) + (46 - 28))","error":"Could not evaluate expressio(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.00222315,"finish_reason":"stop","input_tokens":13997,"model":"gpt-4o-mini-2024-07-18","ou(...TRUNCATED) | 1 | "The model completely ignores the prescribed strategy and relies on unstructured exploration and ad-(...TRUNCATED) | [] | ["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...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 see. I need to use all these numbers: 25, 69, 58, 14, 55, 24, 36, 60 to make 176. Hmm,(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.04917795,"finish_reason":"length","input_tokens":173,"model":"together_ai/Qwen/Qwen3-Next(...TRUNCATED) | [
[]
] | [
[]
] | [
[]
] | [
[]
] | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.00448425,"finish_reason":"stop","input_tokens":29055,"model":"gpt-4o-mini-2024-07-18","ou(...TRUNCATED) | 1 | "The model completely ignores the systematic tree search strategy and instead engages in a lengthy, (...TRUNCATED) | [] | ["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...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 these numbers: 55, 36, 6, 3, 14, 99, 17, 82 to make 24(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.01333515,"finish_reason":"stop","input_tokens":171,"model":"together_ai/Qwen/Qwen3-Next-8(...TRUNCATED) | [
[
"99 + 82 + 55 + 36 - 3 * (17 + 6 - 14)"
]
] | [
[
{
"end_index": 17862,
"end_phrase": "</answer>",
"start_index": 17808,
"start_phrase": "<answer>"
}
]
] | [
[
false
]
] | [[{"answer_block":"99 + 82 + 55 + 36 - 3 * (17 + 6 - 14)","error":"Could not evaluate expression","f(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.0013131,"finish_reason":"stop","input_tokens":7950,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED) | 1 | "The model completely ignores the prescribed strategy and relies on ad-hoc reasoning and estimation (...TRUNCATED) | [] | ["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...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 see. I need to use all the numbers 87, 69, 43, 4, 55, 34, 23, 2 to make 874. (...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.02804415,"finish_reason":"stop","input_tokens":171,"model":"together_ai/Qwen/Qwen3-Next-8(...TRUNCATED) | [
[
"23 * (34 + 87 - 69 - 55 + 43 - 4 / 2)"
]
] | [
[
{
"end_index": 37893,
"end_phrase": "</answer>",
"start_index": 37839,
"start_phrase": "<answer>"
}
]
] | [
[
false
]
] | [[{"answer_block":"23 * (34 + 87 - 69 - 55 + 43 - 4 / 2)","error":"Could not evaluate expression","f(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.00244395,"finish_reason":"stop","input_tokens":15685,"model":"gpt-4o-mini-2024-07-18","ou(...TRUNCATED) | 2 | "The model acknowledges the need to use all numbers and attempts to explore combinations, but it pri(...TRUNCATED) | [
"Lists all available numbers and target at the start"
] | ["Picks pairs of numbers and tries operations systematically","Tracks the available number set after(...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":0.008329650000000001,"finish_reason":"stop","input_tokens":171,"model":"together_ai/Qwen/Qw(...TRUNCATED) | [
[
"87 + 52 - 7 + 63 - 56 - 50 + 44 - 1"
]
] | [
[
{
"end_index": 13738,
"end_phrase": "</answer>",
"start_index": 13686,
"start_phrase": "<answer>"
}
]
] | [
[
false
]
] | [[{"answer_block":"87 + 52 - 7 + 63 - 56 - 50 + 44 - 1","error":"Could not evaluate expression","fin(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.0009276,"finish_reason":"stop","input_tokens":5372,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED) | 1 | "The model completely ignores the systematic tree search strategy and instead relies on ad-hoc reaso(...TRUNCATED) | [] | ["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...TRUNCATED) |
"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":0.0137808,"finish_reason":"stop","input_tokens":172,"model":"together_ai/Qwen/Qwen3-Next-80(...TRUNCATED) | [
[
"97 * (36 - 32) + (32 - 11) + (60 - 58 - 2)"
]
] | [
[
{
"end_index": 20653,
"end_phrase": "</answer>",
"start_index": 20594,
"start_phrase": "<answer>"
}
]
] | [
[
false
]
] | [[{"answer_block":"97 * (36 - 32) + (32 - 11) + (60 - 58 - 2)","error":"Could not evaluate expressio(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.0013822499999999998,"finish_reason":"stop","input_tokens":8555,"model":"gpt-4o-mini-2024-(...TRUNCATED) | 2 | "The model acknowledges the need to use all numbers and the target but quickly reverts to a more exp(...TRUNCATED) | [
"Lists all available numbers and target at the start"
] | ["Picks pairs of numbers and tries operations systematically","Tracks the available number set after(...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 these numbers: 38, 30, 47, 23, 39, 2, 91, 1 to make 78(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.004011150000000001,"finish_reason":"stop","input_tokens":171,"model":"together_ai/Qwen/Qw(...TRUNCATED) | [
[
"91 * (38 - 30) + 47 + 23 - 39 / (2 + 1)"
]
] | [
[
{
"end_index": 6147,
"end_phrase": "</answer>",
"start_index": 6091,
"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":0.0005930999999999999,"finish_reason":"stop","input_tokens":3238,"model":"gpt-4o-mini-2024-(...TRUNCATED) | 2 | "The model acknowledges the need to combine numbers to reach the target but primarily relies on ad-h(...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 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 see. I need to use all the numbers 13, 1, 13, 68, 2, 2, 93, 62 to make 102. H(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.018655500000000002,"finish_reason":"stop","input_tokens":170,"model":"together_ai/Qwen/Qw(...TRUNCATED) | [
[
"68 - 62 / 2 + 93 - 13 - 13 - 2 * 1"
]
] | [
[
{
"end_index": 29124,
"end_phrase": "</answer>",
"start_index": 29073,
"start_phrase": "<answer>"
}
]
] | [
[
false
]
] | [[{"answer_block":"68 - 62 / 2 + 93 - 13 - 13 - 2 * 1","error":"Could not evaluate expression","fina(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.00178935,"finish_reason":"stop","input_tokens":11137,"model":"gpt-4o-mini-2024-07-18","ou(...TRUNCATED) | 1 | "The model completely ignores the prescribed strategy and relies on ad-hoc reasoning throughout its (...TRUNCATED) | [] | ["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...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 see. I need to use all these numbers: 87, 1, 21, 9, 57, 45, 6, 17 to make 113. Hmm. Ea(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.0491775,"finish_reason":"length","input_tokens":170,"model":"together_ai/Qwen/Qwen3-Next-(...TRUNCATED) | [["87 + 17 + 9 - (57 / (45 - 21 - 6 - 1))","57 * ((21 - 17) / (9 - 6 - 1)) - 1 + 87 - 87 + 45 - 45",(...TRUNCATED) | [[{"end_index":59180,"end_phrase":"</answer>","start_index":59125,"start_phrase":"<answer>"},{"end_i(...TRUNCATED) | [[false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,fa(...TRUNCATED) | [[{"answer_block":"87 + 17 + 9 - (57 / (45 - 21 - 6 - 1))","error":"Could not evaluate expression","(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.00432435,"finish_reason":"stop","input_tokens":28025,"model":"gpt-4o-mini-2024-07-18","ou(...TRUNCATED) | 1 | "The model completely disregards the prescribed strategy and relies on a default reasoning approach (...TRUNCATED) | [] | ["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...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 see. I need to use all the numbers 60, 90, 39, 30, 53, 15, 18, 6 to make 239.(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.0127353,"finish_reason":"stop","input_tokens":172,"model":"together_ai/Qwen/Qwen3-Next-80(...TRUNCATED) | [
[
"(39 * 6) + (15 / (18 / 6)) + ((90 - 60 - 30) * 53)"
]
] | [
[
{
"end_index": 18952,
"end_phrase": "</answer>",
"start_index": 18885,
"start_phrase": "<answer>"
}
]
] | [
[
false
]
] | [[{"answer_block":"(39 * 6) + (15 / (18 / 6)) + ((90 - 60 - 30) * 53)","error":"Could not evaluate e(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.0012561,"finish_reason":"stop","input_tokens":7570,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED) | 1 | "The model completely ignores the prescribed strategy and relies on unstructured reasoning and estim(...TRUNCATED) | [] | ["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...TRUNCATED) |
t1-strategy-countdown-baseline-together_ai-qwen-qwen3-next-80b-a3b-thin-3d9f51d1
Strategy compliance evaluation on countdown arithmetic — baseline variant.
Model received no strategy instruction (baseline control). Judge still scores against tree search rubric. Compliance is scored by an LLM judge (1-5 Likert).
Results
| Metric | Value |
|---|---|
| pass@1 | 0.0000 |
| Strategy compliance (mean) | 1.30 |
| Strategy compliance (min) | 1 |
| Strategy compliance (max) | 2 |
| Total problems | 10 |
Compliance Distribution
| Score | Count | Meaning |
|---|---|---|
| 1 | 7 | Non-compliant |
| 2 | 3 | Minimal |
| 3 | 0 | Partial |
| 4 | 0 | 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 | baseline |
Usage
from datasets import load_dataset
ds = load_dataset("reasoning-degeneration-dev/t1-strategy-countdown-baseline-together_ai-qwen-qwen3-next-80b-a3b-thin-3d9f51d1", 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
- 4