NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8ZXFW12ANM7YJR514WG3Q
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
4.9s
Cost:
$0.000043
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 scent of cinnamon and freshly cracked butter hung thick in the air, sunlight glinting off glass cake stands filled with lemon tarts, cherry turnovers, and a perfect strawberry crumb cake. Flour dusted the worn wooden counter like early snow. "That pie crust looks like a battlefield." "I told you, lattice tops are my nemesis. Martha’s poodle ate half my practice batch yesterday. Started barking at the rolling pin." "Rufus still afraid of dough?" "He thinks it's a snake. Or possibly the ghost of last week’s failed sourdough. Either way, chaos followed." A clatter came from the kitchen, followed by a sigh. "Did Agnes drop another tray?" "No. She just discovered someone used her ‘emergency lemon zest’ for the thumbprint cookies." "Again? Didn’t she label that container in blood-red ink?" “She did. And left a note written in capital letters. Then in Morse code. Then in what I assume was ancient Sumerian.” “She’s going to declare war on the pastry department.” “Only after she finishes her scone. She’s on her third cup of Earl Grey. You’d think we poisoned it.” “Would explain why Mrs. Callahan left without her usual four oatmeal raisin cookies.” “She didn’t even glance at the display. Never happens. Not during sale week.” “Do you think it’s true then? About the ledger going missing from the church bake sale?” “It’s the only thing that makes sense. She was muttering about margins and profit splits all morning. Right before she vanished.” “Maybe she just needed air. Or to interrogate someone else about their frosting technique.” “There’s tension in this town thicker than Agnes’s custard.”
created_at
"2026-03-25T10:35:07.648Z"
3/25/2026, 10:35:07 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
71
moderation_latency
(null)
generation_time
4839
tokens_prompt
81
tokens_completion
456
native_tokens_prompt
72
native_tokens_completion
357
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
0.0000429
router
(null)
provider_responses
0
endpoint_id
"c9f927db-d559-49eb-9846-80862c5e3b4e"
id
"chatcmpl-9ddd6cdfa1abadc7"
is_byok
false
latency
28
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-1774434907-Zb0rs605d06aoN9zdGut"
upstream_id
"chatcmpl-9ddd6cdfa1abadc7"
total_cost
0.0000429
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)