NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-22-01KS875NNVZESB86GPK10736ZF
Run Details
Model:
Qwen3.7 Max
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
52.8s
Cost:
$0.028935
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
"Did you actually use the bitter almond extract?" "Of course I did. It’s my grandmother’s secret recipe. Why are you looking at me like that?" "Because Arthur Penhaligon just collapsed at the vicarage tea party." A heavy thud echoed from the back room as a sack of flour hit the wooden floorboards. The sweet, comforting scent of rising dough and caramelized sugar hung thick in the warm air, completely at odds with the news. "Arthur? But he only ever eats the lemon tarts." "He took a bite of your scone just to be polite. Then he turned purple, clutched his chest, and tipped backward into the prize-winning hydrangeas." "Purple? Are you absolutely certain it wasn't just a bad reaction to the jam?" "Positive. And his teacup was completely empty, smelling faintly of marzipan." The oven timer dinged, a sharp, cheerful sound that cut through the sudden, heavy silence of the bakery. "Well, don't just stand there staring at the display case. Grab the tasting spoons." "You want me to eat one?" "If we’re going to figure out what killed him before the inspector arrives, we need to know exactly what it tasted like."
created_at
"2026-05-22T16:09:23.913Z"
5/22/2026, 4:09:23 PM
model
"qwen/qwen3.7-max-20260520"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
895
moderation_latency
(null)
generation_time
52714
tokens_prompt
81
tokens_completion
3189
native_tokens_prompt
78
native_tokens_completion
3832
native_tokens_completion_images
(null)
native_tokens_reasoning
3561
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
0.028935
router
(null)
provider_responses
0
endpoint_id
"6d30fdc6-f2a7-4bdf-b6ba-32353496d723"
id
"chatcmpl-3cb6893c-d58b-968a-9fd2-5842cff3fddf"
is_byok
false
latency
894
model_permaslug
"qwen/qwen3.7-max-20260520"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer
(null)
request_id
"req-1779466163-HHQ1wnTLvVN5CwDFOVvQ"
session_id
(null)
api_type
"completions"
id
"gen-1779466163-i6RwMfhUfO49YnHxVy4F"
upstream_id
"chatcmpl-3cb6893c-d58b-968a-9fd2-5842cff3fddf"
total_cost
0.028935
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)