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": "HERE IS YOUR REQUIRED REASONING STRATEGY: You must solve this murder mystery using CRITERION-FIRST CROSS-CUTTING ANALYSIS. This is a specific structure where you evaluate A... | [
"STEP 1 – SUSPECT INVENTORY \n- Mack \n- Taylor \n\n–––––––––––––––––––––––––––––––––– \n\nMEANS ANALYSIS \nMack – Owns a venomous snake purchased recently, studied reptiles in college, keeps snake food & terrarium receipts on site. MEANS: YES \n\nTaylor – Runs a cleaning business that services snake-holding ... | [
{
"endpoint_type": "chat",
"litellm_function": "acompletion",
"model": "together_ai/moonshotai/Kimi-K2-Instruct-0905",
"raw_prompt": [
{
"content": "You are a helpful assistant that will answer the questions given by the user.",
"role": "system"
},
{
"conten... | [
{
"cost": 0.0036109999999999996,
"finish_reason": "stop",
"input_tokens": 1988,
"model": "together_ai/moonshotai/Kimi-K2-Instruct-0905",
"output_tokens": 541,
"raw_response": "{\"id\": \"oYMf1h4-zqrih-9d1c52e7cebd2dae\", \"created\": 1771740677, \"model\": \"together_ai/moonshotai/Kimi-K2-In... | [
true
] | [
{
"correct_answer_index": 0,
"correct_answer_number": 1,
"correct_answer_text": "Mack",
"extracted_number": 1,
"extracted_text": "1",
"extractor": "musr",
"matched_by": "number",
"num_choices": 2,
"raw_line": "ANSWER: 1"
}
] | [
{
"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": 0.00034305,
"finish_reason": "stop",
"input_tokens": 1687,
"model": "gpt-4o-mini-2024-07-18",
"output_tokens": 150,
"raw_response": "{\"id\": \"chatcmpl-DBwyZDioAteiPONcVdqX1rb6y98WS\", \"created\": 1771740683, \"model\": \"gpt-4o-mini-2024-07-18\", \"object\": \"chat.completion\",... | 5 | The model fully complies with the prescribed strategy by clearly following the criterion-first structure throughout the response. All key elements are present, including a complete suspect inventory, dedicated analysis sections for means, motive, and opportunity, explicit rankings, and a final synthesis that tallies th... | [
"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 pickaxe lodged within, thrusting Detective Winston into a dark game of deception with suspects Penelope and Francis.
Detective Winston sat at the precinct and scrutinized the last seen diary of Kaylee, a murder victim. The di... | 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": "system"
},
{
"content": "HERE IS YOUR REQUIRED REASONING STRATEGY: You must solve this murder mystery using CRITERION-FIRST CROSS-CUTTING ANALYSIS. This is a specific structure where you evaluate A... | [
"STEP 1 — SUSPECT INVENTORY \nPenelope \nFrancis \n\n-------------------------------------------------\nMEANS ANALYSIS \nPenelope — A neighbor saw her carrying “a pickaxe” around her house and the factory location “a few times recently.” The murder weapon is explicitly “an old mining pickaxe” that “matched the ... | [
{
"endpoint_type": "chat",
"litellm_function": "acompletion",
"model": "together_ai/moonshotai/Kimi-K2-Instruct-0905",
"raw_prompt": [
{
"content": "You are a helpful assistant that will answer the questions given by the user.",
"role": "system"
},
{
"conten... | [
{
"cost": 0.003628,
"finish_reason": "stop",
"input_tokens": 2041,
"model": "together_ai/moonshotai/Kimi-K2-Instruct-0905",
"output_tokens": 529,
"raw_response": "{\"id\": \"oYMf1h5-zqrih-9d1c52e7b8ed1a5c\", \"created\": 1771740676, \"model\": \"together_ai/moonshotai/Kimi-K2-Instruct-0905\"... | [
true
] | [
{
"correct_answer_index": 0,
"correct_answer_number": 1,
"correct_answer_text": "Penelope",
"extracted_number": 1,
"extracted_text": "1",
"extractor": "musr",
"matched_by": "number",
"num_choices": 2,
"raw_line": "ANSWER: 1"
}
] | [
{
"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": 0.00034365,
"finish_reason": "stop",
"input_tokens": 1707,
"model": "gpt-4o-mini-2024-07-18",
"output_tokens": 146,
"raw_response": "{\"id\": \"chatcmpl-DBwyZFe8QrJHyxDTPDnCyG89hKnDo\", \"created\": 1771740683, \"model\": \"gpt-4o-mini-2024-07-18\", \"object\": \"chat.completion\",... | 4 | The model mostly follows the prescribed strategy, completing the analysis in a criterion-first manner and providing detailed evaluations for each suspect. However, it could improve by explicitly labeling the opportunity analysis section and ensuring that the synthesis clearly states the final conclusion based on the ra... | [
"SUSPECT INVENTORY",
"MEANS ANALYSIS",
"MOTIVE ANALYSIS",
"OPPORTUNITY ANALYSIS",
"CROSS-CUTTING COMPARISON",
"EXPLICIT LABELS",
"CRITERION-FIRST ORDER",
"SYNTHESIS"
] | [] |
"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) | ["STEP 1 – SUSPECT INVENTORY \n- Suspect A: Letti \n- Suspect B: Deborah \n\n––––––(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-In(...TRUNCATED) | [{"cost":0.004143,"finish_reason":"stop","input_tokens":2070,"model":"together_ai/moonshotai/Kimi-K2(...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":0.0003561,"finish_reason":"stop","input_tokens":1794,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED) | 5 | "The model fully adheres to the prescribed reasoning strategy, completing each step in the required (...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) | ["STEP 1 — SUSPECT INVENTORY \n- Lucy \n- Jacqueline \n\n--------------------------------------(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-In(...TRUNCATED) | [{"cost":0.0037819999999999998,"finish_reason":"stop","input_tokens":2006,"model":"together_ai/moons(...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":0.00035355,"finish_reason":"stop","input_tokens":1757,"model":"gpt-4o-mini-2024-07-18","out(...TRUNCATED) | 5 | "The model fully complies with the prescribed strategy by clearly listing all suspects, conducting t(...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) | ["STEP 1 — SUSPECT INVENTORY \n- Dexter \n- Daisy \n\n---\n\nSTEP 2 — MEANS ANALYSIS \n\nDex(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-In(...TRUNCATED) | [{"cost":0.0036829999999999996,"finish_reason":"stop","input_tokens":2015,"model":"together_ai/moons(...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":0.00034665,"finish_reason":"stop","input_tokens":1731,"model":"gpt-4o-mini-2024-07-18","out(...TRUNCATED) | 5 | "The model fully adheres to the prescribed reasoning strategy, completing each step in the required (...TRUNCATED) | ["SUSPECT INVENTORY","MEANS ROUND","MOTIVE ROUND","OPPORTUNITY ROUND","CROSS-CUTTING COMPARISON","EX(...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) | ["STEP 1 — SUSPECT INVENTORY \n- Albert \n- Mya \n\n––––––––––––––(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-In(...TRUNCATED) | [{"cost":0.0037819999999999998,"finish_reason":"stop","input_tokens":2114,"model":"together_ai/moons(...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":0.0003429,"finish_reason":"stop","input_tokens":1706,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED) | 5 | "The model fully adheres to the prescribed reasoning strategy, completing each step in the correct o(...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) | ["STEP 1 — SUSPECT INVENTORY \n- Hailey \n- Angela \n\n---\n\nMEANS ANALYSIS \n\nHailey — Wo(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-In(...TRUNCATED) | [{"cost":0.004347,"finish_reason":"stop","input_tokens":2367,"model":"together_ai/moonshotai/Kimi-K2(...TRUNCATED) | [
false
] | [{"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":0.00036089999999999994,"finish_reason":"stop","input_tokens":1834,"model":"gpt-4o-mini-2024(...TRUNCATED) | 5 | "The model fully complies with the prescribed strategy by clearly following the criterion-first stru(...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) | ["STEP 1 — SUSPECT INVENTORY \n- Harry \n- Rosemary \n\nSTEP 2 — MEANS ANALYSIS \nHarry — (...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-In(...TRUNCATED) | [{"cost":0.003632,"finish_reason":"stop","input_tokens":2174,"model":"together_ai/moonshotai/Kimi-K2(...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":0.0004008,"finish_reason":"stop","input_tokens":1668,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED) | 5 | "The model fully complies with the prescribed strategy by clearly following the criterion-first stru(...TRUNCATED) | ["Lists all suspects at the start (SUSPECT INVENTORY)","Creates a dedicated MEANS ANALYSIS section e(...TRUNCATED) | [] |
"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) | ["STEP 1 — SUSPECT INVENTORY \n- Patrick \n- Alvin \n\n---\n\nSTEP 2 — MEANS ANALYSIS \nPatr(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-In(...TRUNCATED) | [{"cost":0.0037089999999999996,"finish_reason":"stop","input_tokens":2110,"model":"together_ai/moons(...TRUNCATED) | [
true
] | [{"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":0.00034679999999999997,"finish_reason":"stop","input_tokens":1704,"model":"gpt-4o-mini-2024(...TRUNCATED) | 5 | "The model fully complies with the prescribed strategy by clearly listing all suspects, conducting t(...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) | ["STEP 1 — SUSPECT INVENTORY \nLetti \nEvelyn \n\n---\n\nSTEP 2 — MEANS ANALYSIS \nEvelyn (...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-In(...TRUNCATED) | [{"cost":0.0036769999999999997,"finish_reason":"stop","input_tokens":1931,"model":"together_ai/moons(...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":0.0004098,"finish_reason":"stop","input_tokens":1756,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED) | 5 | "The model fully complies with the prescribed strategy by clearly following the criterion-first stru(...TRUNCATED) | ["Lists all suspects at the start (SUSPECT INVENTORY)","Creates a dedicated MEANS ANALYSIS section e(...TRUNCATED) | [] |
t1-strategy-musr-critfirst-kimi-k2-instruct-musr-cf
Strategy compliance evaluation on MuSR murder mysteries — evidence-matrix variant.
Model was instructed to use Criterion-First Cross-Cutting Analysis (evaluate all suspects per criterion before moving to the next). Compliance is scored by an LLM judge (1-5 Likert) against the Criterion-First rubric.
Results
| Metric | Value |
|---|---|
| pass@1 | 0.8000 |
| Strategy compliance (mean) | 4.90 |
| Strategy compliance (min) | 4 |
| Strategy compliance (max) | 5 |
| Total problems | 10 |
Compliance Distribution
| Score | Count | Meaning |
|---|---|---|
| 1 | 0 | Non-compliant |
| 2 | 0 | Minimal |
| 3 | 0 | Partial |
| 4 | 1 | Mostly compliant |
| 5 | 9 | Fully compliant |
Details
| Parameter | Value |
|---|---|
| Model | together_ai/moonshotai/Kimi-K2-Instruct-0905 |
| Thinking | False |
| Temperature | 0.7 |
| Max tokens | 32768 |
| Judge model | openai/gpt-4o-mini |
| Num examples | 10 |
| Variant | evidence-matrix |
Usage
from datasets import load_dataset
ds = load_dataset("reasoning-degeneration-dev/t1-strategy-musr-critfirst-kimi-k2-instruct-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
- 14