NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBF10ZXFRMQSW9KRN3BA8TX
Run Details
Model:
Qwen 3.5 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 48s
Cost:
$0.026461
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
96.8246%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly adjusted her wig nervously. "Okay, the kid turns six at noon. We hit the house at one." Bill checked his watch closely. "Why the long delay?" "Nap time now. The parents will be exhausted. Less security." "And the loot?" "Every single box under the tree. Legos, dolls." "We can't sell dolls." "We melt them down. Gold plating." "That is not how plastic works." "Don't be a stickler. We need cash." "What about the clown?" "I will wear the nose. You wear the shoes." "I hate balloons." "Then you handle the cake." "I'm allergic to frosting." "Then we eat the cake and steal the presents." "That's a plan." "Did we bring the van?" "Yes, parked in the alley." "Wait, why are we stealing presents?" "Because they're wrapped." "No, because the parents won't notice until next Christmas." "It's June." "Exactly. Confusion is our best friend." "What if the kid wakes up?" "Tell him it's a magic trick." "I'm not good with kids." "Just smile and offer candy." "I brought candy?" "You always bring candy." "It's for emergencies." "Like this?" "Sure." "Let's go." The wind blew. They looked. Now. Bill grabbed his bag.
created_at
"2026-02-25T22:34:30.786Z"
2/25/2026, 10:34:30 PM
model
"qwen/qwen3.5-27b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
503
moderation_latency
(null)
generation_time
108071
tokens_prompt
77
tokens_completion
8560
native_tokens_prompt
76
native_tokens_completion
11016
native_tokens_completion_images
(null)
native_tokens_reasoning
10704
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
0.0264612
router
(null)
provider_responses
0
endpoint_id
"f3f88554-0c22-4d57-973b-0dec948808e8"
id
"chatcmpl-6a480246-0e35-95d6-924b-9c359c50ba5d"
is_byok
false
latency
503
model_permaslug
"qwen/qwen3.5-27b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772058870-Bha6ns457qY9ziQlLz8n"
upstream_id
"chatcmpl-6a480246-0e35-95d6-924b-9c359c50ba5d"
total_cost
0.0264612
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
100.00%
Dialogue to Total Word Ratio
Ratio: 89.53%, Deviation: 0.47%
neededClean
false
wordsTotal
191
wordsDialogue
171
96.8246%