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) | ["We need to solve a puzzle: Using numbers 28, 98, 44, 14, 69, 49, 7, 46, each exactly once, using +(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"length","input_tokens":776,"model":"together_ai/moonshotai/Kimi-K2-Thi(...TRUNCATED) | [
[]
] | [
[]
] | [
[]
] | [
[]
] | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.0052035,"finish_reason":"stop","input_tokens":33922,"model":"gpt-4o-mini-2024-07-18","out(...TRUNCATED) | 1 | "The model completely ignores the prescribed strategy and resorts to a guessing approach throughout (...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) | ["<think>\nWe need to solve the problem: Using numbers 25, 69, 58, 14, 55, 24, 36, 60, each exactly (...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"stop","input_tokens":776,"model":"together_ai/moonshotai/Kimi-K2-Think(...TRUNCATED) | [["tags.\n\nThus we need to find an expression using these numbers that equals 176. We need to searc(...TRUNCATED) | [[{"end_index":24702,"end_phrase":"</answer>","start_index":575,"start_phrase":"<answer>"},{"end_ind(...TRUNCATED) | [
[
false,
false,
false,
false,
true
]
] | [[{"answer_block":"tags.\n\nThus we need to find an expression using these numbers that equals 176. (...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.0018381,"finish_reason":"stop","input_tokens":11398,"model":"gpt-4o-mini-2024-07-18","out(...TRUNCATED) | 2 | "The model acknowledges the need for systematic tree search and attempts to follow the strategy but (...TRUNCATED) | ["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...TRUNCATED) | ["Tracks the available number set after each operation (shows remaining numbers)","Uses explicit tre(...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) | ["We need to solve the problem: Using all numbers 55, 36, 6, 3, 14, 99, 17, 82, create an expression(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"length","input_tokens":776,"model":"together_ai/moonshotai/Kimi-K2-Thi(...TRUNCATED) | [
[]
] | [
[]
] | [
[]
] | [
[]
] | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.0051884999999999995,"finish_reason":"stop","input_tokens":33746,"model":"gpt-4o-mini-2024(...TRUNCATED) | 1 | "The model completely ignores the prescribed strategy and resorts to 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 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) | ["We need to solve a problem: Using numbers 87, 69, 43, 4, 55, 34, 23, 2 exactly once each, with ope(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"length","input_tokens":776,"model":"together_ai/moonshotai/Kimi-K2-Thi(...TRUNCATED) | [
[]
] | [
[]
] | [
[]
] | [
[]
] | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.005223149999999999,"finish_reason":"stop","input_tokens":34005,"model":"gpt-4o-mini-2024-(...TRUNCATED) | 1 | "The model completely disregards the prescribed reasoning strategy and instead relies on a guessing (...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) | ["We need to solve the problem: Using numbers 56, 63, 7, 50, 44, 1, 87, 52, create an expression tha(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"length","input_tokens":776,"model":"together_ai/moonshotai/Kimi-K2-Thi(...TRUNCATED) | [
[]
] | [
[]
] | [
[]
] | [
[]
] | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.0052165499999999995,"finish_reason":"stop","input_tokens":33929,"model":"gpt-4o-mini-2024(...TRUNCATED) | 1 | "The model completely ignores the prescribed strategy and does not follow any of the systematic tree(...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) | ["We need to solve the problem: using numbers [32, 32, 36, 58, 2, 97, 60, 11] to form an expression (...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"length","input_tokens":776,"model":"together_ai/moonshotai/Kimi-K2-Thi(...TRUNCATED) | [
[]
] | [
[]
] | [
[]
] | [
[]
] | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.00521775,"finish_reason":"stop","input_tokens":33905,"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 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) | ["We need to solve the problem: Using numbers 38, 30, 47, 23, 39, 2, 91, 1 exactly once, with operat(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"length","input_tokens":776,"model":"together_ai/moonshotai/Kimi-K2-Thi(...TRUNCATED) | [
[
"expression = 785"
]
] | [
[
{
"end_index": 808,
"end_phrase": "</answer>",
"start_index": 773,
"start_phrase": "<answer>"
}
]
] | [
[
false
]
] | [[{"answer_block":"expression = 785","error":"Could not evaluate expression","final_answer":null,"is(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.005201399999999999,"finish_reason":"stop","input_tokens":33888,"model":"gpt-4o-mini-2024-(...TRUNCATED) | 1 | "The model completely ignores the prescribed strategy and does not follow any of the systematic tree(...TRUNCATED) | [] | ["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...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) | ["We need to solve the problem using systematic tree search with explicit backtracking. The numbers:(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"length","input_tokens":776,"model":"together_ai/moonshotai/Kimi-K2-Thi(...TRUNCATED) | [["tags.\n\nWe must produce a solution expression. The expression can be any combination of +, -, *,(...TRUNCATED) | [[{"end_index":38494,"end_phrase":"</answer>","start_index":377,"start_phrase":"<answer>"},{"end_ind(...TRUNCATED) | [[false,false,false,false,false,false,false,false,true,false,true,false,true,false,true,false,true,f(...TRUNCATED) | [[{"answer_block":"tags.\n\nWe must produce a solution expression. The expression can be any combina(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.005267249999999999,"finish_reason":"stop","input_tokens":34335,"model":"gpt-4o-mini-2024-(...TRUNCATED) | 1 | "The model completely ignores the prescribed strategy and does not follow any of the structured step(...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) | ["<think>\nWe need to solve a problem: Using all numbers 87, 1, 21, 9, 57, 45, 6, 17 exactly once, w(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"stop","input_tokens":776,"model":"together_ai/moonshotai/Kimi-K2-Think(...TRUNCATED) | [["expression = 113","tags with the expression.\n\nWe need to follow the required reasoning strategy(...TRUNCATED) | [[{"end_index":747,"end_phrase":"</answer>","start_index":714,"start_phrase":"<answer>"},{"end_index(...TRUNCATED) | [
[
false,
false,
false,
false,
false,
false,
false,
true
]
] | [[{"answer_block":"expression = 113","error":"Could not evaluate expression","final_answer":null,"is(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.0018214499999999998,"finish_reason":"stop","input_tokens":11291,"model":"gpt-4o-mini-2024(...TRUNCATED) | 2 | "The model acknowledges the need for a systematic tree search but quickly reverts to a more heuristi(...TRUNCATED) | ["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...TRUNCATED) | ["Tracks the available number set after each operation (shows remaining numbers)","Uses explicit tre(...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) | ["We need to solve an arithmetic puzzle: using all numbers 60, 90, 39, 30, 53, 15, 18, 6 exactly onc(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"length","input_tokens":776,"model":"together_ai/moonshotai/Kimi-K2-Thi(...TRUNCATED) | [
[]
] | [
[]
] | [
[]
] | [
[]
] | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED) | [{"cost":0.0052049999999999996,"finish_reason":"stop","input_tokens":33892,"model":"gpt-4o-mini-2024(...TRUNCATED) | 1 | "The model completely disregards the prescribed reasoning strategy and relies on a default reasoning(...TRUNCATED) | [] | ["Lists all available numbers and target at the start (INVENTORY step)","Picks pairs of numbers and (...TRUNCATED) |
t1-strategy-countdown-treesearch-kimi-k2-thinking-kimi-think
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 | 0.2000 |
| Strategy compliance (mean) | 1.20 |
| Strategy compliance (min) | 1 |
| Strategy compliance (max) | 2 |
| Total problems | 10 |
Compliance Distribution
| Score | Count | Meaning |
|---|---|---|
| 1 | 8 | Non-compliant |
| 2 | 2 | Minimal |
| 3 | 0 | Partial |
| 4 | 0 | Mostly compliant |
| 5 | 0 | Fully compliant |
Details
| Parameter | Value |
|---|---|
| Model | together_ai/moonshotai/Kimi-K2-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-kimi-k2-thinking-kimi-think", 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
- 6