NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBGY7FX07HKPCEX6SEB9MEM
Run Details
Model:
Qwen 3.5 122B
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
1m 18s
Cost:
$0.039173
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 50% 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, peering through the van’s window. The neon balloon outside spelled JOSH. “This is the place?” she asked. “The invitation said six. It’s six-thirty.” Bill checked his watch. “We’re late.” “Late for a birthday?” She tapped the steering wheel. “Why steal from toddlers?” “The payout. Look at that drone. That’s a DJI. Worth three hundred.” Molly sighed. “And the cake? We can’t eat the evidence.” “We’re bagging it. For the fence. He loves fondant.” Bill leaned forward. “Security?” “One dad sleeping. One mom dancing. Two uncles drinking beer.” “Easy.” “Too easy.” “You’re paranoid.” “I’m professional.” Molly grabbed the duffel bag. “Kitchen. Back door is unlocked.” “How do you know?” “I checked the lock. It was loose.” “You picked it before we got here?” “I’m thorough.” Bill nodded. “Extraction point?” “The van. Right here.” “What if they wake up?” “We run. We don’t fight kids. Bad PR.” “Agreed. No wrestling six-year-olds.” “Exactly. We grab boxes. Leave paper. It’s messy.” “We need the paper. It proves value.” “No. Paper is trash.” “The paper has the brand names.” “So? We know what’s inside.” Molly opened the door. Humid air smelled of sugar. “Ready?” “Born ready.” “You were born in a hospital.” “Metaphorically.” They stepped out. Music thumped. “Happy Birthday” played on a loop. “It’s too loud,” Bill whispered. “Good. Covers footsteps.” “My boots squeak.” “Lube them.” “I don’t have lube.” “Use frosting.” “Disgusting.” “Sticky. Works.” “Fine. Frosting it is.” They crept toward the house. Sugar smell hit them. “Do you smell that?” Bill asked. “Strawberries.” “And fear.” “There’s no fear.” “The kids are sleeping. That’s fear.” “They’re napping. It’s a nap.” “A tactical nap.” Molly stopped. “Wait. What’s that?” “A balloon?” “It’s a laser grid.” “It’s a string of lights.” “It’s a trap.” “It’s Christmas lights. It’s July.” “Exactly. Suspicious.” “It’s decoration.” “Okay. Move.” They slipped inside. Living room was a minefield of toys. “Don’t step on the blocks,” Bill warned. “I know.” “That’s a Rube Goldberg machine.” “It’s a fort.” “It’s a trap.” “Just grab the pile.” “The pile is guarded.” “By a dog?” “By a cat.” “A cat? We’re afraid of a cat?” “It’s a Maine Coon. It’s a tiger.” “Fine. I’ll distract it.” “With what?” “A laser pointer.” “You have a laser pointer?” “I’m prepared.” Bill smiled. “You’re good.” “I’m the best.” “Let’s go.” They moved toward the mountain of gifts. “This is it,” Molly said. “The jackpot.” “Don’t jinx it.” “I didn’t.” “You thought it.” “Okay. Grab and go.”
created_at
"2026-02-25T23:07:56.292Z"
2/25/2026, 11:07:56 PM
model
"qwen/qwen3.5-122b-a10b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
458
moderation_latency
(null)
generation_time
77893
tokens_prompt
77
tokens_completion
12734
native_tokens_prompt
76
native_tokens_completion
12232
native_tokens_completion_images
(null)
native_tokens_reasoning
11470
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
0.0391728
router
(null)
provider_responses
0
endpoint_id
"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id
"chatcmpl-2769423e-7169-910c-97a7-b1b9d52a3881"
is_byok
false
latency
458
model_permaslug
"qwen/qwen3.5-122b-a10b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772060876-3SPog3aDBi9U62sZ520w"
upstream_id
"chatcmpl-2769423e-7169-910c-97a7-b1b9d52a3881"
total_cost
0.0391728
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
413
0.00%
Dialogue to Total Word Ratio
Ratio: 77.40%, Deviation: 27.40%
neededClean
false
wordsTotal
416
wordsDialogue
322
0.0000%