NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK19BMQRPX6N9BQAENNV1V0
Run Details
Model:
Qwen 3.5 397B A17B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4m 36s
Cost:
$0.041478
Provider:
Alibaba
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 black turtleneck, squinting through binoculars at the bounce house. It seemed overly fortified for a kids birthday. Bill checked lockpicks, nervous sweat beading on his forehead despite the cool night air. They crouched behind a hedge shaped like a dragon. The target was rich in Lego sets and gift cards. Molly lowered the glasses, her expression grim. This was the biggest score of their careers, assuming they did not get caught by a clown. Bill whispered into the darkness. "Are those clown shoes?" Molly nodded, checking her watch. The parents were distracted by cake. The window was unlocked. They moved silently across the lawn, avoiding sprinklers. Bill held the bag open while Molly reached for wrapping paper. It crinkled loudly. They froze. A toddler stared at them from the window. Molly smiled weakly. "Just checking the gifts." The toddler blinked. Bill gestured for a retreat. They backed away empty handed. The security was too tight. Even the infants were very vigilant. Molly sighed, dropping binoculars. "We need the Legos." "Leave the stuffed animals." "But plush pays bills." They would try the baby shower next week. Bill kicked a pebble in frustration. Their reputations were ruined by toddlers.
created_at
"2026-02-16T10:57:13.908713+00:00"
2/16/2026, 10:57:13 AM
model
"qwen/qwen3.5-397b-a17b-20260216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
826
moderation_latency
(null)
generation_time
276262
tokens_prompt
77
tokens_completion
8036
native_tokens_prompt
76
native_tokens_completion
11509
native_tokens_completion_images
(null)
native_tokens_reasoning
11234
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
0.041478
router
(null)
provider_responses
0
id
"chatcmpl-aa9e1cca-212c-9e97-a086-c863c065b8a7"
status
200
is_byok
false
latency
826
endpoint_id
"180484a2-e24b-495a-ba41-b34b680d5a9f"
provider_name
"Alibaba"
model_permaslug
"qwen/qwen3.5-397b-a17b-20260216"
api_type
"completions"
id
"gen-1771239157-mQa0IWh9UA8VqZCBKON3"
upstream_id
"chatcmpl-aa9e1cca-212c-9e97-a086-c863c065b8a7"
total_cost
0.041478
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: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%