NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8C8VJCDT5PS51WRPMN386
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
4.6s
Cost:
$0.000041
Provider:
WandB
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
Flour dusted the air like powdered sugar as golden croissants cooled on wire racks. The scent of cinnamon and yeast clung to every surface. A bell chimed above the door, and the warmth shifted. “You’re in early. Trouble sleeping again?” “Same dream. The red hat by the willow tree, only this time it was humming.” “Humming? Hats don’t hum.” “This one did. Low, like a hymn. And someone left a jar of pickled beets outside my door last night. No note.” “Beets? You hate beets.” “Exactly.” Silence stretched, broken only by the tick of the oven timer. “Did you hear about Martha’s cat? Vanished two mornings ago. Then showed up yesterday, neatly groomed, with a lace doily tied around its neck.” “A doily?” “Pink. Monogrammed. Initials were ‘E.R.’” “Evelyn Riley? She’s been knitting those for weeks. Said they were gifts.” “She doesn’t even like cats.” Another pause. A loaf cracked in the cooling rack. “You don’t suppose… she’s collecting them? The hat, the beets, the cat…” “You’re not suggesting Evelyn Riley’s in the business of small-town paranormal kidnapping?” “I’m just saying—she bakes lemon tarts no one dares eat. Claims they’re ‘blessed.’” “Hmm. I always thought her buttercream was suspiciously smooth.” “Coincidence?” “Or craftsmanship.” Footsteps echoed on the tiled floor. The bell chimed again. “Close the shutters early tonight.”
created_at
"2026-03-25T10:24:23.927Z"
3/25/2026, 10:24:23 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
73
moderation_latency
(null)
generation_time
4478
tokens_prompt
81
tokens_completion
414
native_tokens_prompt
72
native_tokens_completion
334
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
0.0000406
router
(null)
provider_responses
0
endpoint_id
"c9f927db-d559-49eb-9846-80862c5e3b4e"
id
"chatcmpl-a1d8bf9663cf54bd"
is_byok
false
latency
33
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"WandB"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434263-b4aHqF3q7EUIsNhNRxHY"
upstream_id
"chatcmpl-a1d8bf9663cf54bd"
total_cost
0.0000406
cache_discount
(null)
upstream_inference_cost
0
provider_name
"WandB"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)