NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBG69F7VG8BGJTBJ004FCDK
Run Details
Model:
Qwen 3.5 122B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
57.1s
Cost:
$0.026031
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The bell above the door remained silent, the whole town holding its breath. The scent of burnt sugar and yeast hung heavy in the air, masking the very sharp tang of anxiety. Morning light filtered through the glass display case, illuminating dust motes dancing over rows of untouched danishes. The coffee machine hissed quietly in the corner, a lonely sound in the empty shop. "You look like you haven't slept since the coroner left." "Sleep is overrated anyway. Besides, the sourdough won't rise itself." "Is it true? He was found in the flour bin?" "Don't joke about that. It wasn't funny then, and it isn't funny now." "I'm not joking. Mrs. Gable says she saw him arguing with the baker's apprentice." "Mrs. Gable thinks the mailman steals garden gnomes. Take her word with a grain of salt." "Still the apprentice left the back door at midnight." "I was there. I was kneading dough." "Alibi?" "Flour on my apron. Blood on my conscience?" "That's grim. Even for you." "Someone wanted him dead. The question is why." "The will?" "Always the will." "I'll bring you a fresh warm croissant. On the house." "Keep it. I need to think deeply." "Fine. But don't let the truth go cold." "The truth is always cold and bitter." The oven timer dinged loudly.
created_at
"2026-02-25T22:54:51.883Z"
2/25/2026, 10:54:51 PM
model
"qwen/qwen3.5-122b-a10b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
459
moderation_latency
(null)
generation_time
57006
tokens_prompt
81
tokens_completion
6796
native_tokens_prompt
78
native_tokens_completion
8125
native_tokens_completion_images
(null)
native_tokens_reasoning
7802
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0260312
router
(null)
provider_responses
0
endpoint_id
"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id
"chatcmpl-0b0bd01d-5ada-9d85-97c5-dd86768e4fe8"
is_byok
false
latency
459
model_permaslug
"qwen/qwen3.5-122b-a10b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772060091-pQmyDyKP5ToFsDpTIbVd"
upstream_id
"chatcmpl-0b0bd01d-5ada-9d85-97c5-dd86768e4fe8"
total_cost
0.0260312
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)