NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8AC13F21RE0ZHGZVS4NF2
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
4.2s
Cost:
$0.000039
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 early snow, catching in the golden light that spilled through the front windows. The scent of cinnamon and yeast wrapped around the room, warm and familiar. "You know, I found Mrs. Pembleton’s cat sleeping in the bread oven again this morning. Not turned on, of course. Just curled right up in there like it’s her personal throne." "Only in this town. Though, I can’t blame her—your brioche does have a certain hypnotic warmth." "Ha. Tell that to my insurance adjuster. He says one spark and the whole place goes up." "Still, better than finding a ghost in the flour bin like last week. You ever figure out who left those old theater bills in the back shelf?" "Martha swears she didn’t. But I caught her humming show tunes yesterday behind the counter. Suspicious, if you ask me." "Everyone’s suspicious when free scones are involved. Speaking of—did you make the lavender ones?" "Fresh this morning. But not a crumb leaves this counter until you tell me who’s been stealing the cookie samples when Doris isn’t looking." "Cross my heart. But I did see someone in a postal uniform sneaking a double chocolate chunk behind the hydrangeas." "Roy? That sweet old mailman?" "Sweet as pie. But pie with a secret agenda." A laugh rang out, echoing against the ceramic tiles. Outside, church bells marked the hour, and another customer pushed through the door, jingling the little bell overhead.
created_at
"2026-03-25T10:23:21.639Z"
3/25/2026, 10:23:21 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
65
moderation_latency
(null)
generation_time
4178
tokens_prompt
81
tokens_completion
380
native_tokens_prompt
72
native_tokens_completion
322
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
0.0000394
router
(null)
provider_responses
0
endpoint_id
"c9f927db-d559-49eb-9846-80862c5e3b4e"
id
"chatcmpl-aca6ea3f3f7cb45d"
is_byok
false
latency
21
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-1774434201-tiCsRZstdLQQQZiQ9hs2"
upstream_id
"chatcmpl-aca6ea3f3f7cb45d"
total_cost
0.0000394
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)