NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBDQWRGVGPNHRFEY0CWVK8A
Run Details
Model:
Qwen 3.5 35B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
29.5s
Cost:
$0.011185
Provider:
Alibaba
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 dust danced in the shafts of morning light slicing through the tall bakery windows, illuminating the organized chaos of a busy morning prep. The scent of roasted coffee, warm yeast, and caramelized sugar hung heavy in the humid air. Steam curled off the tray she wiped vigorously with a ragged cloth before setting it down on the stainless steel counter with a heavy, final clatter. "You’re staring at the back door again. The lock is fine." "Just watching the time. The morning delivery is usually here by eight." "It’s eight-thirty. The engine should be idling by now." "Perhaps the truck got stuck in the mud." "The road hasn’t been muddy in weeks. You know that. It’s been dry for months." She reached for a rolling pin and cracked it against her palm lightly. "Don’t start with the suspicion again. It doesn’t suit a morning this bright." "Bright days are often the darkest." "That’s not comforting, Martha. Please. I’m just trying to be helpful." "Then don’t expect comfort from the baker." "I just want to know if the shipment arrived." "The shipment? You mean the special order for the Mayor?" "Yes. The one marked ‘confidential.’" "I didn’t sign for anything marked like that. I saw a plain cardboard box though. Near the flour sacks." "That’s where it should be." "Is it?" "You think someone swiped it?" "I think the bakery was robbed yesterday. Or worse." "Then where is the evidence?" "Hidden inside the sourdough loaves. Wrapped in the parchment paper." "In the loaves? You’re joking. That’s ridiculous." "Would I joke about murder in the middle of the kitchen?" "Not in front of the customers." "No. We’ll have to wait until closing. The town is too small for secrets." "Fine. But first, a croissant?" "Only if you can swear it’s safe to eat." "It tastes fine." "Taste isn’t enough. It never is." "Maybe you're overthinking the dough." "Maybe the dough is thinking for me." "That makes no sense." "That’s what makes it perfect." "You’re impossible." "I’m just the baker."
created_at
"2026-02-25T22:12:02.965Z"
2/25/2026, 10:12:02 PM
model
"qwen/qwen3.5-35b-a3b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
415
moderation_latency
(null)
generation_time
29362
tokens_prompt
81
tokens_completion
6078
native_tokens_prompt
78
native_tokens_completion
5583
native_tokens_completion_images
(null)
native_tokens_reasoning
5092
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
0.0111855
router
(null)
provider_responses
0
endpoint_id
"48c1210f-b7d2-4688-a340-f7424fc99d2b"
id
"chatcmpl-f4be96c5-a5f8-9131-9caf-2d2dc43573df"
is_byok
false
latency
415
model_permaslug
"qwen/qwen3.5-35b-a3b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772057522-pJ3tEwYCAhi2YlG9kMDU"
upstream_id
"chatcmpl-f4be96c5-a5f8-9131-9caf-2d2dc43573df"
total_cost
0.0111855
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)