NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK152E1Z1S8E077MMMEFP1Q
Run Details
Model:
Qwen 3.5 Plus (2026-02-15)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.7s
Cost:
$0.000626
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 oversized clown nose, the red foam smelling faintly of regret and cheap plastic. Bill tugged at his polka-dot suspenders, which dug deeply into his soft midsection as he crouched behind a decorative hedge shaped like a dragon. The target was a chaotic explosion of primary colors and sugar-fueled energy known as Tommy's sixth birthday bash. Inside, twenty tiny humans screamed with the intensity of a jet engine while parents snapped photos with blind optimism. Their mission was simple yet morally questionable: infiltrate the gift table, disguised as entertainment, and abscond with the mountain of wrapped treasures before the cake cutting. Molly checked her watch, a tiny plastic thing that had stopped working years ago, signaling it was time. They moved with the grace of drunken elephants, creeping toward the glittering hoard. A woman in a sparkly dress turned, eyeing them suspiciously. Bill froze, attempting to blend in by holding a balloon animal he had accidentally crushed. Molly whispered the plan one last time to ensure synchronization. "Go." They lunged forward, arms wide, ready to scoop up the loot while shouting about magic tricks. The chaos of the party provided perfect cover for their grand, ridiculous theft.
created_at
"2026-02-16T10:50:29.102896+00:00"
2/16/2026, 10:50:29 AM
model
"qwen/qwen3.5-plus-20260216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
871
moderation_latency
(null)
generation_time
11633
tokens_prompt
77
tokens_completion
314
native_tokens_prompt
78
native_tokens_completion
248
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.0006264
router
(null)
provider_responses
0
id
"chatcmpl-1b34b04c-80ef-9566-819e-f6c246e6f196"
status
200
is_byok
false
latency
870
endpoint_id
"71e0f6c3-7815-4734-92d3-8a04f3b0ca91"
provider_name
"Alibaba"
model_permaslug
"qwen/qwen3.5-plus-20260216"
api_type
"completions"
id
"gen-1771239016-IWw8cwXTirgSLjZHUhNJ"
upstream_id
"chatcmpl-1b34b04c-80ef-9566-819e-f6c246e6f196"
total_cost
0.0006264
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
44.2480%
Dialogue to Total Word Ratio
Ratio: 0.50%, Deviation: 9.50%
neededClean
false
wordsTotal
201
wordsDialogue
1
72.1235%