NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFDJS7PBJSH856PSBBBRWRD
Run Details
Model:
Qwen 3.5 9B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
2m 38s
Cost:
$0.001446
Provider:
Together
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 morning sun filtered through the shop windows, illuminating motes of flour dancing in heavy air thick with cinnamon and panic. Martha wiped down the glass display case, her hand trembling slightly. "He's back." "Who is he?" "The baker who vanished." A jar of jam shifted under the open drawer, rattling gently against the wall. "Maybe he just came to say hi." "I don't think strangers come to say hi when the key is in their pocket." Martha tossed a heavy apron onto the dirty counter, grease smearing across the stain. "Mr. Grimes always pays in person." "Is he paying today?" "Just a slip." "A single one? Just like that?" "Five dollars. Cash." "Grimes never carried cash." "What did you say?" "The job we can't afford." Martha's white knuckles tightened around the rag, her face cold. "No one knows how he got it." "Except the one hiding under the floorboard." "You think someone hid something?" "Or moved something?" "Maybe he went to the mill." "For flour?" "Or to leave in the dust." The register beeped loudly, signaling a new customer entered the room. "Answer it." "No." "Answer it." "He's an old man nobody knows." "Someone's scared." "He's afraid." "Afraid of what exactly?" "Of being seen."
created_at
"2026-03-11T21:41:55.075Z"
3/11/2026, 9:41:55 PM
model
"qwen/qwen3.5-9b-20260310"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2552
moderation_latency
(null)
generation_time
157988
tokens_prompt
81
tokens_completion
7791
native_tokens_prompt
78
native_tokens_completion
9587
native_tokens_completion_images
(null)
native_tokens_reasoning
7469
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
0.00144585
router
(null)
provider_responses
0
endpoint_id
"00d506d9-a5e9-4382-a2b9-d54732365594"
id
"oagPFYq-6Ng1vN-9dadb9db50a4f0a0"
is_byok
false
latency
2552
model_permaslug
"qwen/qwen3.5-9b-20260310"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773265315-Xu4JWarMxliBaG2xTCkj"
upstream_id
"oagPFYq-6Ng1vN-9dadb9db50a4f0a0"
total_cost
0.00144585
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)