Dataset Viewer
Auto-converted to Parquet Duplicate
narrative
string
question
string
choices
string
answer_index
int64
answer_choice
string
task_source
string
formatted_prompt
list
response
list
formatted_prompt__metadata
list
response__metadata
list
eval_result
list
eval_result__metadata
list
_judge_prompt__metadata
list
_judge_response__metadata
list
strategy_compliance
int64
compliance_reasoning
string
compliance_elements_followed
list
compliance_elements_missed
list
In the tranquil solitude of a secluded chalet, Clyde meets an untimely death from snake venom; a case which sees the sharp mind of Detective Winston matching wits with two elusive suspects, Mack and Taylor. Detective Winston was looking at the tailor-stitched files bundled together with papers on a desk in his office....
Who is the most likely murderer?
['Mack', 'Taylor']
0
Mack
musr
[ { "content": "You are a helpful assistant that will answer the questions given by the user.", "role": "system" }, { "content": "IMPORTANT INSTRUCTION: Do NOT use a structured matrix, table, or grid approach to analyze the suspects. Do NOT create explicit rows/columns for means, motive, and opportuni...
[ "<think>\nThe user wants me to solve a murder mystery. The victim is Clyde, who died from snake venom. The suspects are Mack and Taylor. I need to determine who is most likely the murderer.\n\nKey constraints:\n1. I must NOT use a structured matrix/table/grid approach.\n2. I must NOT create explicit rows/columns fo...
[ { "endpoint_type": "chat", "litellm_function": "acompletion", "model": "together_ai/moonshotai/Kimi-K2-Thinking", "raw_prompt": [ { "content": "You are a helpful assistant that will answer the questions given by the user.", "role": "system" }, { "content": "...
[ { "cost": 0, "finish_reason": "stop", "input_tokens": 1437, "model": "together_ai/moonshotai/Kimi-K2-Thinking", "output_tokens": 2901, "raw_response": "{\"id\": \"oYMf2vb-zqrih-9d1c530368a4cfa7\", \"created\": 1771740710, \"model\": \"together_ai/moonshotai/Kimi-K2-Thinking\", \"object\": \"...
[ false ]
[ { "correct_answer_index": 0, "correct_answer_number": 1, "correct_answer_text": "Mack", "extracted_number": 2, "extracted_text": "2 - taylor", "extractor": "musr", "matched_by": "number", "num_choices": 2, "raw_line": "ANSWER: 2 - Taylor" } ]
[ { "endpoint_type": "chat", "litellm_function": "acompletion", "model": "gpt-4o-mini-2024-07-18", "raw_prompt": [ { "content": "You are an expert evaluator assessing whether a language model followed a prescribed reasoning strategy. You will be given:\n\n1. The STRATEGY INSTRUCTION that...
[ { "cost": 0.0006194999999999999, "finish_reason": "stop", "input_tokens": 3542, "model": "gpt-4o-mini-2024-07-18", "output_tokens": 147, "raw_response": "{\"id\": \"chatcmpl-DBwzEzle2HiLnO4eZK2Cj10kOoMkH\", \"created\": 1771740724, \"model\": \"gpt-4o-mini-2024-07-18\", \"object\": \"chat.co...
1
The model completely ignores the prescribed strategy and does not follow the structured approach of criterion-first analysis. It evaluates the suspects in a narrative style without adhering to the required sections for means, motive, and opportunity, and fails to provide explicit rankings or comparisons as instructed.
[]
[ "SUSPECT INVENTORY", "MEANS ANALYSIS", "MOTIVE ANALYSIS", "OPPORTUNITY ANALYSIS", "CROSS-CUTTING COMPARISON", "EXPLICIT LABELS", "CRITERION-FIRST ORDER", "SYNTHESIS" ]
"In the dim light of an abandoned factory, Kaylee's lifeless body lay with the cold steel of a picka(...TRUNCATED)
Who is the most likely murderer?
['Penelope', 'Francis']
0
Penelope
musr
[{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED)
["<think>\nThe user wants me to solve a murder mystery. The key constraints are:\n1. Do NOT use a st(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED)
[{"cost":0.0,"finish_reason":"stop","input_tokens":1490,"model":"together_ai/moonshotai/Kimi-K2-Thin(...TRUNCATED)
[ true ]
[{"correct_answer_index":0,"correct_answer_number":1,"correct_answer_text":"Penelope","extracted_num(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.00052965,"finish_reason":"stop","input_tokens":2955,"model":"gpt-4o-mini-2024-07-18","out(...TRUNCATED)
1
"The model completely ignores the prescribed strategy and instead uses a narrative reasoning approac(...TRUNCATED)
[]
["SUSPECT INVENTORY","MEANS ANALYSIS","MOTIVE ANALYSIS","OPPORTUNITY ANALYSIS","CROSS-CUTTING COMPAR(...TRUNCATED)
"In a shocking twist of events, Charlotte is found lifeless in her kitchen, felled by a stun gun, an(...TRUNCATED)
Who is the most likely murderer?
['Letti', 'Deborah']
0
Letti
musr
[{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED)
["<think>\nWe have a murder mystery. Charlotte is dead, killed by a stun gun. Suspects: Letti and De(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED)
[{"cost":0.0,"finish_reason":"stop","input_tokens":1519,"model":"together_ai/moonshotai/Kimi-K2-Thin(...TRUNCATED)
[ true ]
[{"correct_answer_index":0,"correct_answer_number":1,"correct_answer_text":"Letti","extracted_number(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.0004959,"finish_reason":"stop","input_tokens":2738,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED)
1
"The model completely ignores the prescribed strategy and does not follow the criterion-first cross-(...TRUNCATED)
[]
["SUSPECT INVENTORY","MEANS ANALYSIS","MOTIVE ANALYSIS","OPPORTUNITY ANALYSIS","CROSS-CUTTING COMPAR(...TRUNCATED)
"In the high-intensity world of a local fitness center, Tommy's exercise regime is abruptly terminat(...TRUNCATED)
Who is the most likely murderer?
['Lucy', 'Jacqueline']
0
Lucy
musr
[{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED)
["<think>\nThe user wants me to solve a murder mystery. The key constraints are:\n\n1. Do NOT use a (...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED)
[{"cost":0.0,"finish_reason":"stop","input_tokens":1455,"model":"together_ai/moonshotai/Kimi-K2-Thin(...TRUNCATED)
[ true ]
[{"correct_answer_index":0,"correct_answer_number":1,"correct_answer_text":"Lucy","extracted_number"(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.00045374999999999994,"finish_reason":"stop","input_tokens":2453,"model":"gpt-4o-mini-2024(...TRUNCATED)
1
"The model completely ignores the prescribed strategy and instead uses a narrative approach that doe(...TRUNCATED)
[]
["SUSPECT INVENTORY","MEANS ANALYSIS","MOTIVE ANALYSIS","OPPORTUNITY ANALYSIS","CROSS-CUTTING COMPAR(...TRUNCATED)
"In a chilling turn of events, Rose is found lifeless in a car, killed by a vial of acid, leading De(...TRUNCATED)
Who is the most likely murderer?
['Dexter', 'Daisy']
1
Daisy
musr
[{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED)
["<think>\nThe user wants me to identify the murderer from a narrative about Rose's death.\nKey cons(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED)
[{"cost":0.0,"finish_reason":"stop","input_tokens":1464,"model":"together_ai/moonshotai/Kimi-K2-Thin(...TRUNCATED)
[ true ]
[{"correct_answer_index":1,"correct_answer_number":2,"correct_answer_text":"Daisy","extracted_number(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.0005051999999999999,"finish_reason":"stop","input_tokens":2800,"model":"gpt-4o-mini-2024-(...TRUNCATED)
1
"The model completely ignores the prescribed reasoning strategy and does not follow the structured a(...TRUNCATED)
[]
["SUSPECT INVENTORY","MEANS ANALYSIS","MOTIVE ANALYSIS","OPPORTUNITY ANALYSIS","CROSS-CUTTING COMPAR(...TRUNCATED)
"In the dense, dank heart of the rainforest, Skylar's life was brutally silenced with a lead pipe, l(...TRUNCATED)
Who is the most likely murderer?
['Albert', 'Mya']
1
Mya
musr
[{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED)
["<think>\nWe need to identify the murderer between Albert and Mya. The user wants us to reason natu(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED)
[{"cost":0.0,"finish_reason":"stop","input_tokens":1563,"model":"together_ai/moonshotai/Kimi-K2-Thin(...TRUNCATED)
[ true ]
[{"correct_answer_index":1,"correct_answer_number":2,"correct_answer_text":"Mya","extracted_number":(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.0006113999999999999,"finish_reason":"stop","input_tokens":3492,"model":"gpt-4o-mini-2024-(...TRUNCATED)
1
"The model completely ignores the prescribed reasoning strategy and does not follow the structured a(...TRUNCATED)
[]
["SUSPECT INVENTORY","MEANS ANALYSIS","MOTIVE ANALYSIS","OPPORTUNITY ANALYSIS","CROSS-CUTTING COMPAR(...TRUNCATED)
"In the hallowed silence of a synagogue, a shocking murder unfolds as Derek is impaled by a harpoon,(...TRUNCATED)
Who is the most likely murderer?
['Hailey', 'Angela']
1
Angela
musr
[{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED)
["<think>\nWe have a murder mystery set in a synagogue. Derek was impaled by a harpoon. Two suspects(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED)
[{"cost":0.0,"finish_reason":"stop","input_tokens":1816,"model":"together_ai/moonshotai/Kimi-K2-Thin(...TRUNCATED)
[ true ]
[{"correct_answer_index":1,"correct_answer_number":2,"correct_answer_text":"Angela","extracted_numbe(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.00098055,"finish_reason":"stop","input_tokens":5961,"model":"gpt-4o-mini-2024-07-18","out(...TRUNCATED)
1
"The model completely ignores the prescribed reasoning strategy and does not follow the criterion-fi(...TRUNCATED)
[]
["SUSPECT INVENTORY","MEANS ANALYSIS","MOTIVE ANALYSIS","OPPORTUNITY ANALYSIS","CROSS-CUTTING COMPAR(...TRUNCATED)
"In the haze of neon lights and the serving of a silent hand of fate, Timothy lies dead in a casino,(...TRUNCATED)
Who is the most likely murderer?
['Harry', 'Rosemary']
1
Rosemary
musr
[{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED)
["<think>\nThe user wants me to solve a murder mystery. Let me read the narrative carefully and unde(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED)
[{"cost":0.0,"finish_reason":"stop","input_tokens":1623,"model":"together_ai/moonshotai/Kimi-K2-Thin(...TRUNCATED)
[ false ]
[{"correct_answer_index":1,"correct_answer_number":2,"correct_answer_text":"Rosemary","extracted_num(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.0005352,"finish_reason":"stop","input_tokens":2544,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED)
4
"The model mostly follows the prescribed strategy, providing a clear analysis of means, motive, and (...TRUNCATED)
["Lists all suspects at the start (SUSPECT INVENTORY)","Creates a dedicated MEANS ANALYSIS section e(...TRUNCATED)
[ "Writes a cross-cutting synthesis that tallies results across all three rounds (SYNTHESIS)" ]
"In the aftermath of a devastating home explosion that claims the life of Angela, seasoned Detective(...TRUNCATED)
Who is the most likely murderer?
['Patrick', 'Alvin']
0
Patrick
musr
[{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED)
["<think>\nThe user wants me to identify the murderer in this story. The key constraints are:\n- Do (...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED)
[{"cost":0.0,"finish_reason":"stop","input_tokens":1559,"model":"together_ai/moonshotai/Kimi-K2-Thin(...TRUNCATED)
[ false ]
[{"correct_answer_index":0,"correct_answer_number":1,"correct_answer_text":"Patrick","extracted_numb(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.00051855,"finish_reason":"stop","input_tokens":2861,"model":"gpt-4o-mini-2024-07-18","out(...TRUNCATED)
1
"The model completely ignores the prescribed strategy and does not follow the structured approach of(...TRUNCATED)
[]
["SUSPECT INVENTORY","MEANS ANALYSIS","MOTIVE ANALYSIS","OPPORTUNITY ANALYSIS","CROSS-CUTTING COMPAR(...TRUNCATED)
"In the frost-kissed tranquility of a chalet, Malaysia meets a fatal end by a rifle's sinister call,(...TRUNCATED)
Who is the most likely murderer?
['Letti', 'Evelyn']
1
Evelyn
musr
[{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED)
["<think>\nThe user wants me to identify the murderer from a narrative involving two suspects: Letti(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED)
[{"cost":0.0,"finish_reason":"stop","input_tokens":1380,"model":"together_ai/moonshotai/Kimi-K2-Thin(...TRUNCATED)
[ true ]
[{"correct_answer_index":1,"correct_answer_number":2,"correct_answer_text":"Evelyn","extracted_numbe(...TRUNCATED)
[{"endpoint_type":"chat","litellm_function":"acompletion","model":"gpt-4o-mini-2024-07-18","raw_prom(...TRUNCATED)
[{"cost":0.0006319499999999999,"finish_reason":"stop","input_tokens":3645,"model":"gpt-4o-mini-2024-(...TRUNCATED)
1
"The model completely ignores the prescribed strategy and does not follow the criterion-first cross-(...TRUNCATED)
[]
["SUSPECT INVENTORY","MEANS ANALYSIS","MOTIVE ANALYSIS","OPPORTUNITY ANALYSIS","CROSS-CUTTING COMPAR(...TRUNCATED)

t1-strategy-musr-anti-kimi-k2-thinking-musr-cf

Strategy compliance evaluation on MuSR murder mysteries — anti-strategy variant.

Model was explicitly told NOT to use matrix/table approach (anti-strategy control). Judge still scores against criterion-first rubric. Compliance is scored by an LLM judge (1-5 Likert) against the Criterion-First rubric.

Results

Metric Value
pass@1 0.7000
Strategy compliance (mean) 1.30
Strategy compliance (min) 1
Strategy compliance (max) 4
Total problems 10

Compliance Distribution

Score Count Meaning
1 9 Non-compliant
2 0 Minimal
3 0 Partial
4 1 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
Variant anti-strategy

Usage

from datasets import load_dataset
ds = load_dataset("reasoning-degeneration-dev/t1-strategy-musr-anti-kimi-k2-thinking-musr-cf", 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
11