NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBEF9W0NNV6W6H3C9XY2GM2
Run Details
Model:
Qwen 3.5 122B
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
1m 26s
Cost:
$0.043240
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 checked the blueprint taped to the steering wheel. "This is the target, Bill. The Johnson house." Bill gripped the dashboard. "It’s a six-year-old’s birthday, Molly. He wants a robot dog." "And we want the robot dog," she said. "And the Nintendo Switch. And the Lego set." "That’s... that’s just mean." "It’s logistics. They won't miss it until after the cake." "The cake?" "Exactly. By the time they realize the toys are gone, we'll be three states away." Bill sighed. "What about the parents?" "Sleeping. We checked the security feed. Dad is snoring on the couch. Mom is in the kitchen." "So we just walk in?" "We don't walk. We glide." "Gliding is harder than walking." "Not for a master thief." Molly adjusted her black mask. "Are you ready?" "I have a question." "Make it quick." "Do we take the balloons?" "Bill, focus." "They're helium. They float away. It's a hazard." "Leave the balloons. Take the boxes." "What about the piñata?" "Full of candy. Too heavy." "Candy is heavy?" "Sugar weighs something." "Okay, fine. No candy." "Good. Now, the plan. You distract the dog." "The dog?" "There’s a Golden Retriever named Buster." "I can't distract a dog." "You have treats in your pocket." "I have dog biscuits." "Perfect." "What if he bites me?" "Then you scream." "That isn't very professional." "It keeps you alive." "And if the kid wakes up?" "Then you tell him it's a surprise from the Tooth Fairy." "The Tooth Fairy doesn't steal toys." "Tonight she does." Bill looked at the house. Lights were off. "Are we really doing this?" "Yes." "To a birthday party?" "Specifically." "Molly, this feels wrong." "It feels like money." "It feels like a felony." "It feels like payday." "I hate payday." "Stop talking and grab the bag." "Which bag?" "The duffel." "The black one?" "Yes." "Okay." "Move." "Wait." "What now?" "Do we need gloves?" "We always need gloves." "Right." "Bill, please." "Coming." "And Bill?" "Yeah?" "Don't eat the cake." "I wouldn't dare." "Good." "Let's go."
created_at
"2026-02-25T22:24:50.054Z"
2/25/2026, 10:24:50 PM
model
"qwen/qwen3.5-122b-a10b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
396
moderation_latency
(null)
generation_time
86343
tokens_prompt
77
tokens_completion
12646
native_tokens_prompt
76
native_tokens_completion
13503
native_tokens_completion_images
(null)
native_tokens_reasoning
12931
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
0.04324
router
(null)
provider_responses
0
endpoint_id
"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id
"chatcmpl-f48c7050-6573-9e52-98a7-97f26ba9942d"
is_byok
false
latency
396
model_permaslug
"qwen/qwen3.5-122b-a10b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772058290-fSIoDJsXBv0WbgqnSiVb"
upstream_id
"chatcmpl-f48c7050-6573-9e52-98a7-97f26ba9942d"
total_cost
0.04324
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
333
0.00%
Dialogue to Total Word Ratio
Ratio: 91.04%, Deviation: 41.04%
neededClean
false
wordsTotal
335
wordsDialogue
305
0.0000%