NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ89FFPXGXF7KVCJKQ952DA
Run Details
Model:
Qwen 3 32B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
16.4s
Cost:
$0.000195
Provider:
Nebius
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 cinnamon and butter lingered in the air as a bell above the door chimed. “Rough morning?” “You could say that. The usual suspects, probably.” A cup of tea spun in its saucer. “Though someone left a note under my apron hook. Just the word *watch*. No signature.” “Watch for what? Tourists? The mayor’s committee?” “A certain *type* of tourist. You remember that antique locket that went missing last fall?” A flour-dusted hand tapped a newspaper. “Found it in a pie crust this morning. Trapped between the bottom and the tin.” “What kind of pie?” “Apple-raspberry. Mrs. Peabody’s order. She didn’t mention it when she picked it up.” A pause, then a quiet laugh. “Though she did ask if I’d seen *anyone* lingering near the back door lately.” “Anyone specific?” “Think it’s the same person who’s been photographing the historic homes. Always with a camera, always too quiet.” “Maybe they’re writing a guidebook.” “Or casing the town for something else.” A sigh, and the clink of a spoon against china. “Still, I added an extra dash of nutmeg to the scones today. For luck.” “Or for *distracting*.” A reluctant smile. “Someone’s got to keep the gossip lighter than the cookie dough.” Outside, the rain began to patter against the bakery’s windows.
created_at
"2026-03-25T10:22:52.411Z"
3/25/2026, 10:22:52 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
260
moderation_latency
(null)
generation_time
16308
tokens_prompt
98
tokens_completion
720
native_tokens_prompt
73
native_tokens_completion
627
native_tokens_completion_images
(null)
native_tokens_reasoning
359
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
0.0001954
router
(null)
provider_responses
0
endpoint_id
"aaa39b6c-e488-491a-91e4-e5fb66f86601"
id
"cmpl-b0dbbe4924bf303e"
is_byok
false
latency
259
model_permaslug
"qwen/qwen3-32b-04-28"
provider_name
"Nebius"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434172-bRJsakao2yjcJeuKSkLB"
upstream_id
"cmpl-b0dbbe4924bf303e"
total_cost
0.0001954
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Nebius"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)