NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK2SG4DD6PFG22WE37QWS4W
Run Details
Model:
Qwen 3.5 397B A17B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6m 37s
Cost:
$0.056576
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 scanned the very dark fortress illuminated by colorful string lights. The location buzzed with chaotic energy, small humans screaming near a bouncy castle. Bill checked his clipboard, tapping a pen observing the fence. It was merely decorative plastic, easily scalable. He marked the guard rotation: a retriever sleeping near the back door. "Is that a clown?" Bill whispered quietly. "Affirmative. Hostile attire," Molly replied grimly. "What about the piƱata?" she asked softly. "Secondary target. Ignore it." Bill ordered sharply. "Copy that. Moving in now." Molly nodded once firmly. The risk factor just skyrocketed. Parties were notoriously volatile, filled with sugar rushes and unpredictable crying fits. They needed a distraction. Bill produced a bag of premium dog treats from his tactical vest. The plan relied on canine cooperation. Molly checked her watch. Cake cutting commenced in ten minutes, creating the perfect window of opportunity while attention focused on singing. She signaled with two fingers. Bill moved slowly toward the gate, crouching low beneath the hydrangeas. The loot consisted of wrapped boxes containing plastic trucks and dubious skincare sets. It was beneath them, yet the rent was due. They crept forward, shadows lengthening, fully ready to execute the Operation Birthday Blight.
created_at
"2026-02-16T11:25:32.28668+00:00"
2/16/2026, 11:25:32 AM
model
"qwen/qwen3.5-397b-a17b-20260216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
785
moderation_latency
(null)
generation_time
397046
tokens_prompt
77
tokens_completion
12145
native_tokens_prompt
76
native_tokens_completion
15703
native_tokens_completion_images
(null)
native_tokens_reasoning
15435
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
0.0565764
router
(null)
provider_responses
0
id
"chatcmpl-743b2453-7f8e-9b1d-bd68-6dcdb12555e5"
status
200
is_byok
false
latency
785
endpoint_id
"180484a2-e24b-495a-ba41-b34b680d5a9f"
provider_name
"Alibaba"
model_permaslug
"qwen/qwen3.5-397b-a17b-20260216"
api_type
"completions"
id
"gen-1771240734-V6Y2qVRsBt6i0dGqmYYM"
upstream_id
"chatcmpl-743b2453-7f8e-9b1d-bd68-6dcdb12555e5"
total_cost
0.0565764
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%