NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ72ZBVC5HJXXVGHD3YKJT8R
Run Details
Model:
Qwen 3.6 27B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 15s
Cost:
$0.015821
Provider:
Morph
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 bell chimed as the oak door swung shut, leaving vanilla and dark rye hanging in the quiet air. Sunlight caught dust motes above the counter where two figures stood. “The order came again. Same time, same window.” “And still no signature on the ledger.” “Three sourdough loaves, two dozen lemon tarts, exactly one black coffee. No one in the valley drinks it this early.” “Maybe it was for someone else.” “Sent to a route that hasn’t serviced this zip code in twenty years.” “So you think it’s a mistake?” “Mistakes don’t return for refills. I checked the alley bin and found a torn envelope corner. Cream stock, embossed with that old miller’s crest.” “The Henderson mill closed after the flood.” “Closed, maybe. But the cellar doors still swing. Somebody knows our yeast starter matches theirs.” “You really believe a century-old strain is worth breaking into a bakery for?” “Secrets always leave crumbs. Tell me why the back lock sticks only when the humidity drops?” “It’s drafty. I should oil the hinges.” “Oil it then. Leave the starter jar on the top shelf, not the bottom.” “If you’re setting a trap, you’ll have to knead the dough.” “Just make sure the lemons are zested fresh.” “Always.” Outside, a crow called as the oven timer ticked down to zero.
created_at
"2026-04-27T09:05:24.853Z"
4/27/2026, 9:05:24 AM
model
"qwen/qwen3.6-27b-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
912
moderation_latency
(null)
generation_time
75026
tokens_prompt
81
tokens_completion
5395
native_tokens_prompt
78
native_tokens_completion
6574
native_tokens_completion_images
(null)
native_tokens_reasoning
5035
native_tokens_cached
64
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0158205
router
(null)
provider_responses
0
endpoint_id
"826cab4e-dc26-4472-83be-e4ddd5ebd2ab"
id
"f5bb8385f23f42ebad77e2477e169239"
is_byok
false
latency
799
model_permaslug
"qwen/qwen3.6-27b-20260422"
provider_name
"Morph"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777280724-jsD5ZdqHti9H5OFDVmaA"
session_id
(null)
api_type
"completions"
id
"gen-1777280724-DvXZjW3enXzl0z2EEnxO"
upstream_id
"f5bb8385f23f42ebad77e2477e169239"
total_cost
0.0158205
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Morph"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)