NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KXY52ZDBSJ01J6MWEHQN60
Run Details
Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
38.2s
Cost:
$0.006970
Provider:
Novita
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
Warm cinnamon drifted through the tiny bakery, catching dust motes above the marble counter. The oven ticked, and a sheet pan cooled by the window. “Did you hear about Mayor Bell?” “The one who left the library board?” “Yes. His car was found near the old orchard.” “With no keys?” “Just an empty passenger seat and a croissant in the lap.” “A croissant?” “Almond, still warm. The officer said it was impossible, since the bakery opens at six.” “But Mrs. Pyle says she closed at nine.” “So does the register.” A bell above the door jingled, and two paper bags clattered onto the counter. “No more almond croissants today. Something is taking them.” “Taking them?” “Or leaving them where they should not be.” “Could the orchard have made the car stop?” “The brakes were fine. The radio was on, too.” “On what station?” “The classical one. The one only our regulars listen to.” A tray of scones trembled, though no wind stirred the window. “Then we need names,” “Before the next loaf is gone.” “Start with the last person who bought an almond croissant.” “Mrs. Calloway. But she died in spring.” “Then start with who paid for it.”
created_at
"2026-09-03T15:24:28.139Z"
9/3/2026, 3:24:28 PM
model
"qwen/qwen3.8-27b-20260814"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
621
moderation_latency
(null)
generation_time
38114
tokens_prompt
78
tokens_completion
1948
native_tokens_prompt
116
native_tokens_completion
2307
native_tokens_completion_images
(null)
native_tokens_reasoning
2011
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.00696972
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788449068-IRcO400AqmlRC0l3V33B"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788449068-10I5lctcTmPmnTU57O3r"
upstream_id
"ce289ebc07f46bd3606e92390b764ee9"
provider_responses
0
endpoint_id
"2af35fbf-0463-4d96-96d1-1e82b1a46dc7"
id
"ce289ebc07f46bd3606e92390b764ee9"
is_byok
false
latency
620
model_permaslug
"qwen/qwen3.8-27b-20260814"
provider_name
"Novita"
status
200
total_cost
0.00696972
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)