NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK331DQDSW1Z109T7RYWSBS
Run Details
Model:
Qwen 3.5 397B A17B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6m 10s
Cost:
$0.046813
Provider:
Alibaba
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
"Bill, check the perimeter silently," Molly whispered, crouching low behind the hedge. "It's a bounce house, Mol. The perimeter is vinyl." "Perimeter. Now. Check for parents nearby." "Clowns are guarding the gift table." "Clowns? Actual clowns with shoes?" "Balloon animals. Sharp edges. Potential weapons." "We hit during cake service. Distraction is required." "I'm not singing Happy Birthday again." "You will if you want the Lego sets." "Fine. What's the exit strategy this time?" "Slide down the inflatable castle rear entrance." "I'm too heavy for the slide." "Diet later, steal now. Physics is optional." "The wrapping paper crinkles loudly." "Wear gloves. Use the silent rip technique." "This feels morally wrong, Mol." Bill sighed very heavily. "They're insured. Parents love insurance payouts." "What about the heavy piƱata?" "Secondary target. Candy surplus holds value." "Kids will cry." "Tears build character ultimately." "Okay, but no hurting the hired magician." Molly grinned wickedly. "Promise. Just steal the rabbit." "The rabbit?" "Fur coats are coming back in style." "You're insane." "I'm rich. Ready to move?" "No." "Too late. Move now." "Wait, did you bring the sack?" "Always bring the sack." "It has ducks on it." He nodded quietly. "Quacks distract security." She smiled softly. "Let's go."
created_at
"2026-02-16T11:30:18.164449+00:00"
2/16/2026, 11:30:18 AM
model
"qwen/qwen3.5-397b-a17b-20260216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
801
moderation_latency
(null)
generation_time
369976
tokens_prompt
77
tokens_completion
8918
native_tokens_prompt
76
native_tokens_completion
12991
native_tokens_completion_images
(null)
native_tokens_reasoning
12645
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
0.0468132
router
(null)
provider_responses
0
id
"chatcmpl-ac93f4b9-7bfd-91de-a7e1-3d2845bdb644"
status
200
is_byok
false
latency
801
endpoint_id
"180484a2-e24b-495a-ba41-b34b680d5a9f"
provider_name
"Alibaba"
model_permaslug
"qwen/qwen3.5-397b-a17b-20260216"
api_type
"completions"
id
"gen-1771241047-EjAB8PoiCplMXqyNnGcy"
upstream_id
"chatcmpl-ac93f4b9-7bfd-91de-a7e1-3d2845bdb644"
total_cost
0.0468132
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
100.0000%
Dialogue to Total Word Ratio
Ratio: 90.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
180
100.0000%