NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBG9BYPMD9DR1AT6Q10VTG1
Run Details
Model:
Qwen 3.5 27B
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
1m 13s
Cost:
$0.016381
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 70% 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 night vision goggles, though it was three in the afternoon. Bill sat in the passenger seat of the unmarked van, eating a bag of chips. The perimeter is clear, Molly said. Security is a golden retriever named Buster. Buster is a liability, Bill said, crunching loudly. He licks things. If he licks the lock, we are in trouble. He is distracted by the cake, Molly replied. We have a window of forty five minutes before the parents notice the presents are missing. Forty five minutes to unload a room full of toys, Bill asked. That is tight. It is not just toys, Molly said. It is the LEGO sets. The remote control helicopters. The disappointment of a seven year old boy named Timmy. Timmy is the target, Bill asked. Timmy is the victim, Molly corrected. We are targeting the gifts. Specifically, the ones under the tree. What about the ones in the living room? Those are for the guests, Molly said. We only want the birthday boy haul. Why, Bill asked. We could sell them all. Because the guests gifts are mostly socks and gift cards, Molly said. No resale value on a ten dollar Amazon voucher. Fair point, Bill said. So, how do we get in? Through the window, Molly said. Buster is guarding the door. And the window? It is unlocked, Molly said. The mother left it open for ventilation. Negligence, Bill said. I respect it. We need bags, Molly said. Big ones. I have got the duffels, Bill said. But what about the wrapping paper? Leave it, Molly said. We sell the contents. What about the noise, Bill asked. The balloons pop if we run too fast. We move like ghosts, Molly said. Or like toddlers who just ate too much sugar. I am not eating sugar, Bill said. I am on a diet. You are eating chips, Molly said. You are on a snack diet. Same thing, Bill said. Okay, plan B. If we get caught, what do we say? We say we are delivering pizza, Molly said. They always open the door for pizza. It is not pizza, Bill said. It is a heist. Details, Molly said. Start the van. I need to finish this bag, Bill said. Bill, Molly said. Focus. Okay, okay, Bill said. Engine is running. Good, Molly said. Let us go make Timmy cry. For the greater good, Bill said. For the greater profit, Molly said. Same thing, Bill said. Molly grabbed the crowbar. Bill tossed the chips into the trash. They opened the doors. The van idled quietly. Wait, Bill said. Do you have the list? It is in my head, Molly said. Blue box, red bow, top shelf. Right, Bill said. Top shelf. Bottom shelf is for the parents, Molly said. They are watching the TV. Smart, Bill said. Very smart. We go in now, Molly said. Before the cake. Wait for the cake, Bill asked. No, Molly said. Before. Okay, Bill said. Let us go. They stepped out. The sun was bright. Goggles off, Molly said. Right, Bill said. Do not trip, Molly said. I never trip, Bill said. You tripped last week, Molly said. That was a rug, Bill said. It was a floor, Molly said. Semantics, Bill said. Move, Molly said. Moving, Bill said. They walked toward the house.
created_at
"2026-02-25T22:56:32.731Z"
2/25/2026, 10:56:32 PM
model
"qwen/qwen3.5-27b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
415
moderation_latency
(null)
generation_time
72504
tokens_prompt
77
tokens_completion
6458
native_tokens_prompt
76
native_tokens_completion
6816
native_tokens_completion_images
(null)
native_tokens_reasoning
6012
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
0.0163812
router
(null)
provider_responses
0
endpoint_id
"f3f88554-0c22-4d57-973b-0dec948808e8"
id
"chatcmpl-2c97e705-12a7-9151-b450-94a10170cf48"
is_byok
false
latency
415
model_permaslug
"qwen/qwen3.5-27b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772060192-JmJjHhhnVGKCalMAK3av"
upstream_id
"chatcmpl-2c97e705-12a7-9151-b450-94a10170cf48"
total_cost
0.0163812
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
556
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 70.00%
neededClean
false
wordsTotal
556
wordsDialogue
0
0.0000%