NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFGJY30HTJ1R2RA57Y9DP9E
Run Details
Model:
Qwen 3.5 9B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 37s
Cost:
$0.001007
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 scent of cardamom hung heavy in the damp air, masking the smell of old glue on the rotting floorboards. "Hasn't been here three days straight, haven't you noticed the silence?" "Too much soot on his coat, that's what I noticed first." "The townsfolk aren't talking though." "Nothing about the flour shifting in the bin this morning?" "Just whispers about a new delivery from the outskirts." "Dr. Holmes sent her over, did she leave a card?" "Don't know what you're whispering about inside my head." "Maybe the oven was undercooked entirely." "Or maybe someone's hiding in there." "You didn't hide it under the hamper, right?" "No." "You know I read between the paper lines." "I haven't seen a ghost in my kitchen since November." "Better call the police before we move." "Let them buy the cinnamon rolls first." "We need to find those missing cookies this afternoon." "They vanish one by one in the night." Waiting for the final decision comes with a risk. The customer picked up a warm cup with hands banded by white flour. The owner sighed heavily, wiping down the counter with a rag that smelled distinct from anything in the display case. This trail looked suspiciously like clues waited to be found.
created_at
"2026-03-11T22:34:25.772Z"
3/11/2026, 10:34:25 PM
model
"qwen/qwen3.5-9b-20260310"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
543
moderation_latency
(null)
generation_time
96608
tokens_prompt
81
tokens_completion
6371
native_tokens_prompt
78
native_tokens_completion
6661
native_tokens_completion_images
(null)
native_tokens_reasoning
6035
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
0.00100695
router
(null)
provider_responses
0
endpoint_id
"00d506d9-a5e9-4382-a2b9-d54732365594"
id
"oagfQ9v-6Ng1vN-9dae06c75645f0b5"
is_byok
false
latency
543
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-1773268465-h1pefrlymWmpjScKEa6q"
upstream_id
"oagfQ9v-6Ng1vN-9dae06c75645f0b5"
total_cost
0.00100695
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)