NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8MKQ4MZ6A7REDRA92KE5X
Run Details
Model:
Qwen 3 32B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
6.5s
Cost:
$0.000266
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
60.65%
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
“Well, I heard you finally closed on the old Thompson place.” “Yep. Turns out the price was right for a fixer-upper with ghosts and all.” “You’re actually going to restore it? Not knock it down and build a boutique hotel?” “What kind of fool would do that in this town?” “Right. And the locals would have revolted anyway.” “So, how’s Mrs. Wexley liking her new cinnamon rolls?” “Oh, she swears they cure insomnia. Which is weird, because she’s been sleeping like a log these past few weeks.” “That’s my recipe magic for you.” “I still can’t figure out what you put in your blueberry scones. They’ve got people coming back day after day.” “She probably put in just the right amount of nostalgia,”
someone said
from behind. You both turned to see Mr. Hale leaning against the doorway, holding a paper bag of pastries with the corners slightly crumpled, as if he’d already made a dent in them. “How do you always know when we’re getting serious?”
created_at
"2026-03-25T10:28:57.192Z"
3/25/2026, 10:28:57 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
808
moderation_latency
(null)
generation_time
6485
tokens_prompt
98
tokens_completion
278
native_tokens_prompt
76
native_tokens_completion
215
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.0002656
router
(null)
provider_responses
0
endpoint_id
"2693bf9a-1732-4008-acc9-d241214e936c"
id
"ae0bcddf3aa342239e8ba287c8f7dd33"
is_byok
false
latency
808
model_permaslug
"qwen/qwen3-32b-04-28"
provider_name
"AtlasCloud"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434537-1eo2UULviRVduov1jQfa"
upstream_id
"ae0bcddf3aa342239e8ba287c8f7dd33"
total_cost
0.0002656
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"someone said"