NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBEQJ8546SBTJHHGV07VZ3X
Run Details
Model:
Qwen 3.5 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 28s
Cost:
$0.004499
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.6885%
Overall
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 the plastic clown nose, peering through slats above the fire grate. Bill checked the lockpicker set, humming tune suggesting confidence rather than preparation for the mission. Outside, the children screeched like banshees, playing drums against glass, a percussion section for grand opera of theft. They weren't stealing diamonds today. The prize wall glowed beneath tangled paper streams and ribbons. Bill pointed at the wrapping paper pile on the floor. She nodded, pulling tongs from her boot. The plan was simple. In, out, before cake slicing. They would vanish leaving crumbs of glitter behind. Security was nonexistent. A mom watched television. No alarms triggered by squeaky toys. It felt like pure greed disguised as mischief tonight. Molly glanced at duffel bag on table. Bill checked watch. It was finally time. They moved like shadows in a nursery. The first door creaked. Nothing happened silently. Bill signaled left for them. They slipped past table laden with dolls and legos. The smell of frosting clung to floor. Molly whispered, "We should hurry up and grab the best big presents now." Bill nodded, "Okay but be careful with the dog nearby please." They moved. Success was theirs.
created_at
"2026-02-25T22:29:20.781Z"
2/25/2026, 10:29:20 PM
model
"qwen/qwen3.5-flash-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
476
moderation_latency
(null)
generation_time
88203
tokens_prompt
77
tokens_completion
8616
native_tokens_prompt
76
native_tokens_completion
11229
native_tokens_completion_images
(null)
native_tokens_reasoning
10971
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
0.0044992
router
(null)
provider_responses
0
endpoint_id
"5f6b71b5-8672-4b27-8b2d-f674429f9e63"
id
"chatcmpl-86bc391d-0c51-930a-8f19-c6913c0d95a2"
is_byok
false
latency
476
model_permaslug
"qwen/qwen3.5-flash-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772058560-aLeIb6tdBEeM7yUncVH1"
upstream_id
"chatcmpl-86bc391d-0c51-930a-8f19-c6913c0d95a2"
total_cost
0.0044992
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
100.00%
Dialogue to Total Word Ratio
Ratio: 10.26%, Deviation: 0.26%
neededClean
false
wordsTotal
195
wordsDialogue
20
99.6885%