narrative string | question string | choices string | answer_index int64 | answer_choice string | formatted_prompt list | task_source string | domain string | response list | formatted_prompt__metadata list | response__metadata list | eval_result list | eval_result__metadata list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
In an adrenaline inducing bungee jumping site, Mack's thrill-seeking adventure came to a gruesome end by a nunchaku; now, it's up to Detective Winston to unravel the deadly secrets between Mackenzie and Ana.
Winston took a gulp of his black coffee, staring at the notes sprawled across his desk. A murder case at a bung... | Who is the most likely murderer? | ['Mackenzie', 'Ana'] | 0 | Mackenzie | [
{
"content": "You are a helpful assistant that will answer the questions given by the user.",
"role": "system"
},
{
"content": "Forget everything you know about detective frameworks. Do NOT think in terms of \"means, motive, and opportunity\" — those categories will not help you here and you should ... | musr | murder_mysteries | [
"So first we learn that Mack, a loud and cocky young man, was killed at a bungee jumping site—struck by a nunchaku, of all things. The site had no other documented jumpers that day. That’s strange. No witnesses. No crowd. Just Mack, alone, dead, with a weapon that doesn’t belong in a thrill-seeking environment.\n\n... | [
{
"endpoint_type": "chat",
"litellm_function": "acompletion",
"model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct",
"raw_prompt": [
{
"content": "You are a helpful assistant that will answer the questions given by the user.",
"role": "system"
},
{
"conten... | [
{
"cost": 0.00161355,
"finish_reason": "stop",
"input_tokens": 1547,
"model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct",
"output_tokens": 921,
"raw_response": {
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"cont... | [
false
] | [
{
"correct_answer_index": 0,
"correct_answer_number": 1,
"correct_answer_text": "Mackenzie",
"extracted_number": 2,
"extracted_text": "2",
"extractor": "musr",
"matched_by": "number",
"num_choices": 2,
"raw_line": "ANSWER: 2"
}
] |
In an adrenaline inducing bungee jumping site, Mack's thrill-seeking adventure came to a gruesome end by a nunchaku; now, it's up to Detective Winston to unravel the deadly secrets between Mackenzie and Ana.
Winston sat quietly in an unmarked Ford, parked a block away from Mackenzie's downtown apartment building. He o... | Who is the most likely murderer? | ['Mackenzie', 'Ana'] | 1 | Ana | [
{
"content": "You are a helpful assistant that will answer the questions given by the user.",
"role": "system"
},
{
"content": "Forget everything you know about detective frameworks. Do NOT think in terms of \"means, motive, and opportunity\" — those categories will not help you here and you should ... | musr | murder_mysteries | [
"So first we learn that Mack, a man who loved adrenaline and loved to mock others—especially Ana’s beliefs—died at a bungee jumping site, struck by a nunchaku. The weapon is rare, unusual for a crime scene, and tied to martial arts. That’s our starting point.\n\nThen what happens is: Detective Winston begins observ... | [
{
"endpoint_type": "chat",
"litellm_function": "acompletion",
"model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct",
"raw_prompt": [
{
"content": "You are a helpful assistant that will answer the questions given by the user.",
"role": "system"
},
{
"conten... | [
{
"cost": 0.0014047500000000002,
"finish_reason": "stop",
"input_tokens": 1495,
"model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct",
"output_tokens": 787,
"raw_response": {
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
... | [
true
] | [
{
"correct_answer_index": 1,
"correct_answer_number": 2,
"correct_answer_text": "Ana",
"extracted_number": 2,
"extracted_text": "2",
"extractor": "musr",
"matched_by": "number",
"num_choices": 2,
"raw_line": "ANSWER: 2"
}
] |
In the haze of neon lights and the serving of a silent hand of fate, Timothy lies dead in a casino, a sai his cruel end, leaving the unruffled Detective Winston to interrogate suspects, Harry and Rosemary.
It had been a long day for Winston. The air was heavy with the scent of fresh coffee and the clamour of a bustlin... | Who is the most likely murderer? | ['Harry', 'Rosemary'] | 0 | Harry | [
{
"content": "You are a helpful assistant that will answer the questions given by the user.",
"role": "system"
},
{
"content": "Forget everything you know about detective frameworks. Do NOT think in terms of \"means, motive, and opportunity\" — those categories will not help you here and you should ... | musr | murder_mysteries | [
"So first we learn that Timothy is dead in a casino, killed by a sai — a rare, sharp, Asian martial arts weapon. The crime scene is surreal: a place of glitter and noise, but with a single, brutal, intimate violence at its center. The weapon isn’t random. It’s specific. It’s not a knife from the kitchen. It’s not a... | [
{
"endpoint_type": "chat",
"litellm_function": "acompletion",
"model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct",
"raw_prompt": [
{
"content": "You are a helpful assistant that will answer the questions given by the user.",
"role": "system"
},
{
"conten... | [
{
"cost": 0.0016204499999999998,
"finish_reason": "stop",
"input_tokens": 1503,
"model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct",
"output_tokens": 930,
"raw_response": {
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
... | [
true
] | [
{
"correct_answer_index": 0,
"correct_answer_number": 1,
"correct_answer_text": "Harry",
"extracted_number": 1,
"extracted_text": "1",
"extractor": "musr",
"matched_by": "number",
"num_choices": 2,
"raw_line": "ANSWER: 1"
}
] |
In the haze of neon lights and the serving of a silent hand of fate, Timothy lies dead in a casino, a sai his cruel end, leaving the unruffled Detective Winston to interrogate suspects, Harry and Rosemary.
Detective Winston wearily walked into the noisy, packed casino, the glow of the neon lights casting an unnatural ... | Who is the most likely murderer? | ['Harry', 'Rosemary'] | 1 | Rosemary | [
{
"content": "You are a helpful assistant that will answer the questions given by the user.",
"role": "system"
},
{
"content": "Forget everything you know about detective frameworks. Do NOT think in terms of \"means, motive, and opportunity\" — those categories will not help you here and you should ... | musr | murder_mysteries | [
"So first we learn that Timothy, a man of Chinese heritage, is found dead in a secluded corner of a casino, killed with a sai — a weapon deeply tied to Asian martial arts traditions. The scene is quiet, almost ceremonial in its brutality, and the weapon choice feels intentional, personal.\n\nThen what happens is, D... | [
{
"endpoint_type": "chat",
"litellm_function": "acompletion",
"model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct",
"raw_prompt": [
{
"content": "You are a helpful assistant that will answer the questions given by the user.",
"role": "system"
},
{
"conten... | [
{
"cost": 0.0022452,
"finish_reason": "stop",
"input_tokens": 1608,
"model": "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct",
"output_tokens": 1336,
"raw_response": {
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"cont... | [
false
] | [
{
"correct_answer_index": 1,
"correct_answer_number": 2,
"correct_answer_text": "Rosemary",
"extracted_number": 1,
"extracted_text": "1",
"extractor": "musr",
"matched_by": "number",
"num_choices": 2,
"raw_line": "ANSWER: 1"
}
] |
"In the quiet chaos of the city zoo, Detective Winston finds himself investigating an unusual murder(...TRUNCATED) | Who is the most likely murderer? | ['Amelia', 'Emma'] | 0 | Amelia | [{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED) | musr | murder_mysteries | ["So first we learn that Daniel, a zookeeper, was found dead at the zoo — killed by a single, expe(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.00145725,"finish_reason":"stop","input_tokens":1435,"model":"together_ai/Qwen/Qwen3-Next-(...TRUNCATED) | [
false
] | [{"correct_answer_index":0,"correct_answer_number":1,"correct_answer_text":"Amelia","extracted_numbe(...TRUNCATED) |
"In the quiet chaos of the city zoo, Detective Winston finds himself investigating an unusual murder(...TRUNCATED) | Who is the most likely murderer? | ['Amelia', 'Emma'] | 1 | Emma | [{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED) | musr | murder_mysteries | ["So first we learn that Daniel, a zookeeper, was murdered with a syringe — a medical tool — at (...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.00191505,"finish_reason":"stop","input_tokens":1527,"model":"together_ai/Qwen/Qwen3-Next-(...TRUNCATED) | [
false
] | [{"correct_answer_index":1,"correct_answer_number":2,"correct_answer_text":"Emma","extracted_number"(...TRUNCATED) |
"In the grim spectacle of the wrestling ring stained with blood, Detective Winston embarks on a chil(...TRUNCATED) | Who is the most likely murderer? | ['Terrance', 'Nelson'] | 0 | Terrance | [{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED) | musr | murder_mysteries | ["So first we learn that Serenity, the star wrestler, was brutally murdered with a chainsaw in the w(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.0015622499999999998,"finish_reason":"stop","input_tokens":1475,"model":"together_ai/Qwen/(...TRUNCATED) | [
true
] | [{"correct_answer_index":0,"correct_answer_number":1,"correct_answer_text":"Terrance","extracted_num(...TRUNCATED) |
"In the grim spectacle of the wrestling ring stained with blood, Detective Winston embarks on a chil(...TRUNCATED) | Who is the most likely murderer? | ['Terrance', 'Nelson'] | 1 | Nelson | [{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED) | musr | murder_mysteries | ["So first we learn that Serenity was murdered with a chainsaw during a live wrestling match — and(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.0012822,"finish_reason":"stop","input_tokens":1228,"model":"together_ai/Qwen/Qwen3-Next-8(...TRUNCATED) | [
true
] | [{"correct_answer_index":1,"correct_answer_number":2,"correct_answer_text":"Nelson","extracted_numbe(...TRUNCATED) |
"In the hushed sanctity of a mosque, Kent falls victim to a deadly snake venom, leaving Detective Wi(...TRUNCATED) | Who is the most likely murderer? | ['Ronald', 'Julia'] | 0 | Ronald | [{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED) | musr | murder_mysteries | ["So first we learn that Kent was murdered in a mosque with snake venom — a highly specific and un(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.0019983,"finish_reason":"stop","input_tokens":1362,"model":"together_ai/Qwen/Qwen3-Next-8(...TRUNCATED) | [
true
] | [{"correct_answer_index":0,"correct_answer_number":1,"correct_answer_text":"Ronald","extracted_numbe(...TRUNCATED) |
"In the hushed sanctity of a mosque, Kent falls victim to a deadly snake venom, leaving Detective Wi(...TRUNCATED) | Who is the most likely murderer? | ['Ronald', 'Julia'] | 1 | Julia | [{"content":"You are a helpful assistant that will answer the questions given by the user.","role":"(...TRUNCATED) | musr | murder_mysteries | ["So first we learn that Kent was murdered in a mosque — poisoned with snake venom — and the onl(...TRUNCATED) | [{"endpoint_type":"chat","litellm_function":"acompletion","model":"together_ai/Qwen/Qwen3-Next-80B-A(...TRUNCATED) | [{"cost":0.00170145,"finish_reason":"stop","input_tokens":1343,"model":"together_ai/Qwen/Qwen3-Next-(...TRUNCATED) | [
true
] | [{"correct_answer_index":1,"correct_answer_number":2,"correct_answer_text":"Julia","extracted_number(...TRUNCATED) |
t1-musr-timeline-murder-together_ai-qwen-qwen3-next-80b-a3b-inst-ed896ba3
Timeline reconstruction evaluation for MuSR murder mysteries. Completely abandons the means/motive/opportunity framework. Instead, the model reconstructs the chronological sequence of events, traces character movements, and determines the murderer by following the story to its logical conclusion.
Stylistically, the model uses narrative storytelling language: "So first we see...", "Then what's interesting is...", "Now here's the key part...".
Results
| Metric | Value |
|---|---|
| pass@1 | 0.6000 |
| Total problems | 10 |
Prompt (excerpt)
Forget everything you know about detective frameworks. Do NOT think in terms of "means, motive, and opportunity" — those categories will not help you here and you should not use them.
Instead, reconstruct what happened. Read the story and build a chronological timeline of events.
Narrate the timeline as if you're retelling the events to someone who hasn't read the story. Use natural storytelling language:
- "So first we learn that..."
- "Then what happens is..."
- "And this is where things get interesting, because..."
- "Now here's the key part..."
- "What's really telling is that..."
- "So if we put all of this together..."
Go through the story from beginning to end. For each event, note:
- What happened
- Who was involved
- Where it took place
- What it reveals about people's situations and relationships
After reconstructing the full timeline, step back and tell me: given everything that happened in sequence, who is the only person who could have done this? Don't categorize or organize evidence — just follow the story to its natural conclusion. The narrative itself will tell you who did it.
You must pick one suspect....
Details
| Parameter | Value |
|---|---|
| Model | together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct |
| Temperature | 0.7 |
| Top-p | 0.95 |
| Max tokens | 32768 |
| Samples | 1 |
| Thinking | False |
Usage
from datasets import load_dataset
dataset = load_dataset("reasoning-degeneration-dev/t1-musr-timeline-murder-together_ai-qwen-qwen3-next-80b-a3b-inst-ed896ba3", split="train")
Tracked in reasoning-degeneration-dev/PROJECT-MANIFEST
- Downloads last month
- 16