NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBDWX210AX8MV8VEM5S6RW0
Run Details
Model:
Qwen 3.5 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 22s
Cost:
$0.020970
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
98.51%
Dialogue to Total Word Ratio
(details)
99.2553%
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 mask. Bill checked the blueprints. They stood in the shadows. "The perimeter is weak. Just a pink plastic fence with no alarms." "And the security system? Is it electronic or biological? I need to know the risk." "A toddler named Timmy. He's easily bribed with gummy worms." "I hate relying on sugar. It causes sticky hands. What about the loot?" "Trucks, dolls, and an expensive drone. High resale value." "We need a getaway vehicle. Something fast and untraceable." "The clown car is parked outside. It fits six perfectly." "I look ridiculous in a red nose. It ruins my professional image." "You look ridiculous in a suit. Stick to the nose. It's camouflage." "Fine. When do we strike? Timing is everything in this business." "During the cake cutting. Maximum distraction from the parents." "What if they notice us missing the gifts? They'll call the police." "They won't. They're busy fighting over the piƱata." "And the parents? Are they watching the door?" "Drunk on punch. We're golden. They won't notice anything." "Let's get those toys. I want the drone specifically." "The frosting is white. It hides our footprints nicely." "After you, partner. Don't trip on the confetti. It's slippery."
created_at
"2026-02-25T22:14:47.114Z"
2/25/2026, 10:14:47 PM
model
"qwen/qwen3.5-27b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
458
moderation_latency
(null)
generation_time
81983
tokens_prompt
77
tokens_completion
6853
native_tokens_prompt
76
native_tokens_completion
8728
native_tokens_completion_images
(null)
native_tokens_reasoning
8429
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
0.02097
router
(null)
provider_responses
0
endpoint_id
"f3f88554-0c22-4d57-973b-0dec948808e8"
id
"chatcmpl-14d32dde-e0b8-9082-911c-a9ddee4ce64a"
is_byok
false
latency
458
model_permaslug
"qwen/qwen3.5-27b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772057687-25yNkwonLbdW8hYJpvWg"
upstream_id
"chatcmpl-14d32dde-e0b8-9082-911c-a9ddee4ce64a"
total_cost
0.02097
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
98.51%
Dialogue to Total Word Ratio
Ratio: 93.50%, Deviation: 3.50%
neededClean
false
wordsTotal
200
wordsDialogue
187
99.2553%