NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ90F6DYE6W0600DTT2018P
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
5.2s
Cost:
$0.000042
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
The morning sun slanted through the front window of Buttercup’s Bakery, dusting the case of cinnamon rolls and lemon tarts in gold. The scent of vanilla and fresh butter hung warm in the air. A bell tinkled as the door closed behind the last customer, leaving only the quiet hum of the espresso machine. “Did you hear? Old Mr. Pendergast found Mrs. Calloway’s prize poodle wrapped in tinsel, barking up a storm in his azaleas.” “In tinsel? It’s nearly June.” “Exactly. And get this—he swears he didn’t touch the thing. Says he woke up, opened the door, and there it was. Festive as a misplaced Christmas ornament.” “That dog’s been missing since Tuesday. Mrs. Calloway had flyers all over town. Offered twenty dollars.” “Twenty? She gave me a scone just for promising to keep an eye out. I wonder if someone’s playing a prank.” “Or hiding something. Pendergast’s been acting mighty strange since the Town Hall meeting. Kept muttering about ‘dishonest ledgers’ under his breath.” “You think it’s connected? A dog and town budgets?” “Maybe. Or maybe someone just hates Mrs. Calloway’s rhubarb jam. You know she entered it in the fair last year and beat Doris’s.” “I’d hide a dog in someone’s yard for less. That jam tastes like cough syrup and regret.” A laugh danced through the room, mingling with the clink of a spoon in a teacup. “Still. Tinsel in June. That’s not just a prank. That’s a message.”
created_at
"2026-03-25T10:35:25.777Z"
3/25/2026, 10:35:25 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
70
moderation_latency
(null)
generation_time
5148
tokens_prompt
81
tokens_completion
397
native_tokens_prompt
72
native_tokens_completion
350
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
0.0000422
router
(null)
provider_responses
0
endpoint_id
"c9f927db-d559-49eb-9846-80862c5e3b4e"
id
"chatcmpl-90927d6d4fd9ae94"
is_byok
false
latency
32
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-1774434925-PCKsK29J1tFCN3uVCp2P"
upstream_id
"chatcmpl-90927d6d4fd9ae94"
total_cost
0.0000422
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)