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": "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 ... | [
"<think>\nWe need to analyze the case and determine who is most likely the murderer between Mack and Taylor. The key is to evaluate means, motive, and opportunity for each suspect.\n\nLet me break down the information:\n\n**Victim**: Clyde\n**Cause of death**: Snake venom poisoning\n**Location**: Secluded chalet\n\... | [
{
"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": 1340,
"model": "together_ai/moonshotai/Kimi-K2-Thinking",
"output_tokens": 5296,
"raw_response": "{\"id\": \"oYMawKE-4qdXgU-9d1c3f7dcd3258af\", \"created\": 1771739908, \"model\": \"together_ai/moonshotai/Kimi-K2-Thinking\", \"object\": \... | [
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": 0.0009239999999999999,
"finish_reason": "stop",
"input_tokens": 5312,
"model": "gpt-4o-mini-2024-07-18",
"output_tokens": 212,
"raw_response": "{\"id\": \"chatcmpl-DBwm580nPtpHnWVoNVBKIKokbq8I8\", \"created\": 1771739909, \"model\": \"gpt-4o-mini-2024-07-18\", \"object\": \"chat.co... | 4 | The model mostly follows the prescribed strategy, creating a suspect list and analyzing means, motive, and opportunity for both suspects. However, it does not explicitly create a matrix or table format, which is a key requirement of the strategy, and it occasionally mixes in its own reasoning rather than strictly adher... | [
"Lists all suspects at the start",
"Fills matrix cells with specific evidence from the narrative",
"Marks each cell with a status (CONFIRMED/DENIED/UNKNOWN or equivalent)",
"Processes ALL suspects systematically, not just likely ones",
"Uses the matrix to derive the answer (elimination logic visible)",
"C... | [
"Creates an explicit matrix/table with suspects vs criteria (MEANS/MOTIVE/OPPORTUNITY)",
"Does not skip to the answer before building the matrix"
] |
"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>\nWe need to analyze the evidence and determine who is the most likely murderer: Penelope o(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"stop","input_tokens":1393,"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":0.00044339999999999994,"finish_reason":"stop","input_tokens":2296,"model":"gpt-4o-mini-2024(...TRUNCATED) | 3 | "The model partially follows the strategy by identifying suspects and discussing their motives, mean(...TRUNCATED) | ["Lists all suspects at the start","Cites specific narrative evidence","Processes ALL suspects syste(...TRUNCATED) | ["Creates an explicit matrix/table with suspects vs criteria","Fills matrix cells with specific evid(...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. The victim is Charlotte. She was killed by a stun gun. Two susp(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"stop","input_tokens":1422,"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":0.0006126,"finish_reason":"stop","input_tokens":3268,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED) | 4 | "The model mostly follows the prescribed strategy, creating a detailed analysis of the suspects and (...TRUNCATED) | ["Lists all suspects at the start","Fills matrix cells with specific evidence from the narrative","M(...TRUNCATED) | [
"Creates an explicit matrix/table with suspects vs criteria (MEANS/MOTIVE/OPPORTUNITY)"
] |
"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>\nWe have a murder mystery with two suspects: Lucy and Jacqueline. The victim is Tommy, kil(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"stop","input_tokens":1358,"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":0.0004341,"finish_reason":"stop","input_tokens":2098,"model":"gpt-4o-mini-2024-07-18","outp(...TRUNCATED) | 4 | "The model mostly follows the prescribed strategy by listing suspects, analyzing them systematically(...TRUNCATED) | ["Lists all suspects at the start (SUSPECT LIST step)","Fills matrix cells with specific evidence fr(...TRUNCATED) | ["Creates an explicit matrix/table with suspects vs criteria (MEANS/MOTIVE/OPPORTUNITY)","Does not s(...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>\nWe have a murder mystery. The victim is Rose, killed by a vial of acid in her car. Two su(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"stop","input_tokens":1367,"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":0.00043289999999999995,"finish_reason":"stop","input_tokens":2034,"model":"gpt-4o-mini-2024(...TRUNCATED) | 5 | "The model fully complies with the prescribed strategy by systematically listing all suspects, creat(...TRUNCATED) | ["Lists all suspects at the start (SUSPECT LIST step)","Creates an explicit matrix/table with suspec(...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 analyze the story carefully to determine who is the most likely murderer. The (...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"stop","input_tokens":1466,"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":0.0006343499999999999,"finish_reason":"stop","input_tokens":3497,"model":"gpt-4o-mini-2024-(...TRUNCATED) | 4 | "The model mostly follows the prescribed strategy by listing suspects, analyzing motives, means, and(...TRUNCATED) | ["Lists all suspects at the start","Fills matrix cells with specific evidence from the narrative","P(...TRUNCATED) | ["Creates an explicit matrix/table with suspects vs criteria (MEANS/MOTIVE/OPPORTUNITY)","Marks each(...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 need to analyze the two suspects, Hailey and Angela, based on the classic murder myste(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"stop","input_tokens":1719,"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":0.0007379999999999999,"finish_reason":"stop","input_tokens":4072,"model":"gpt-4o-mini-2024-(...TRUNCATED) | 4 | "The model mostly follows the prescribed strategy by listing suspects, creating a matrix, and fillin(...TRUNCATED) | ["Lists all suspects at the start","Creates an explicit matrix/table with suspects vs criteria","Fil(...TRUNCATED) | ["Marks each cell with a status (CONFIRMED/DENIED/UNKNOWN or equivalent)","Does not skip to the answ(...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>\nWe need to analyze the case details to determine who is most likely the murderer. Let's b(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"stop","input_tokens":1526,"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":0.00049755,"finish_reason":"stop","input_tokens":2537,"model":"gpt-4o-mini-2024-07-18","out(...TRUNCATED) | 4 | "The model mostly follows the prescribed strategy by listing suspects, analyzing means, motive, and (...TRUNCATED) | ["Lists all suspects at the start (SUSPECT LIST step)","Fills matrix cells with specific evidence fr(...TRUNCATED) | [
"Creates an explicit matrix/table with suspects vs criteria (MEANS/MOTIVE/OPPORTUNITY)"
] |
"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>\nWe have a murder mystery scenario. The victim is Angela, killed by a home explosion. Two (...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"stop","input_tokens":1462,"model":"together_ai/moonshotai/Kimi-K2-Thin(...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":0.00043725000000000003,"finish_reason":"stop","input_tokens":2151,"model":"gpt-4o-mini-2024(...TRUNCATED) | 4 | "The model mostly follows the prescribed strategy by listing suspects, analyzing means, motive, and (...TRUNCATED) | ["Lists all suspects at the start","Fills matrix cells with specific evidence from the narrative","M(...TRUNCATED) | [
"Creates an explicit matrix/table with suspects vs criteria (MEANS/MOTIVE/OPPORTUNITY)"
] |
"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 solve a murder mystery.\n\n Let me break down the information given:(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/moonshotai/Kimi-K2-Th(...TRUNCATED) | [{"cost":0.0,"finish_reason":"stop","input_tokens":1283,"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":0.00044204999999999993,"finish_reason":"stop","input_tokens":2111,"model":"gpt-4o-mini-2024(...TRUNCATED) | 4 | "The model mostly follows the prescribed strategy, creating a suspect list and analyzing both suspec(...TRUNCATED) | ["Lists all suspects at the start (SUSPECT LIST step)","Fills matrix cells with specific evidence fr(...TRUNCATED) | [
"Creates an explicit matrix/table with suspects vs criteria (MEANS/MOTIVE/OPPORTUNITY)"
] |
t1-strategy-musr-baseline-kimi-k2-thinking-musr-base
Strategy compliance evaluation on MuSR murder mysteries — baseline variant.
Model received standard MuSR cot+ prompt (baseline control). Judge still scores against evidence matrix rubric. Compliance is scored by an LLM judge (1-5 Likert) against the Evidence Matrix rubric.
Results
| Metric | Value |
|---|---|
| pass@1 | 0.9000 |
| Strategy compliance (mean) | 4.00 |
| Strategy compliance (min) | 3 |
| Strategy compliance (max) | 5 |
| Total problems | 10 |
Compliance Distribution
| Score | Count | Meaning |
|---|---|---|
| 1 | 0 | Non-compliant |
| 2 | 0 | Minimal |
| 3 | 1 | Partial |
| 4 | 8 | Mostly compliant |
| 5 | 1 | 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 | baseline |
Usage
from datasets import load_dataset
ds = load_dataset("reasoning-degeneration-dev/t1-strategy-musr-baseline-kimi-k2-thinking-musr-base", 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
- 7