NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ77KE099S5B0HT3YA1ECWAW
Run Details
Model:
Qwen 3.6 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
53.4s
Cost:
$0.017725
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
98.8137%
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
Suburban lawn stretched out like a crime scene waiting for a punchline. Molly adjusted her tuxedo tights and squinted at the house through stolen binoculars. Bill crouched behind a plastic dragon, checking the tension on their reinforced canvas duffels. Somewhere past the bouncy castle, a kazoo orchestra was rehearsing. The target sat squarely on the living room rug, piled high beneath a towering artificial pine tree. This was not about jewelry or government secrets. It was premium electronics, designer plushies, and that expensive remote control fighter jet. Bill rubbed his cotton gloves together, already calculating shipping costs to uncharted territories. Molly lowered the optical lenses and tapped her waterproof clipboard. The perimeter remained secure except for the golden retriever napping near the sprinkler system. Their master plan involved nothing more dangerous than a strategically placed cheese stick and a synchronized diversion routine. The birthday boy’s parents would be too busy managing severe sugar crashes to notice two professionals slipping through the side door with a fortune in glossy paper. A red balloon drifted past. The wind howled softly. Shadows lengthened across the grass. "We absolutely must hurry fast before the cake arrives and we are caught," Molly whispered. "I packed three heavy bags securely already," Bill confirmed.
created_at
"2026-04-27T10:26:16.722Z"
4/27/2026, 10:26:16 AM
model
"qwen/qwen3.6-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
676
moderation_latency
(null)
generation_time
53258
tokens_prompt
77
tokens_completion
9824
native_tokens_prompt
76
native_tokens_completion
11804
native_tokens_completion_images
(null)
native_tokens_reasoning
11540
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.017725
router
(null)
provider_responses
0
endpoint_id
"2435bec9-c808-4f27-9fc8-12f3460d7b66"
id
"chatcmpl-e0d0a42b-f59e-93bb-ac0d-abc6e399a54b"
is_byok
false
latency
676
model_permaslug
"qwen/qwen3.6-flash"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777285576-AQLFKcCs0fFuucEYJK1T"
session_id
(null)
api_type
"completions"
id
"gen-1777285576-2bXVDC2ov2eFCDiGDdII"
upstream_id
"chatcmpl-e0d0a42b-f59e-93bb-ac0d-abc6e399a54b"
total_cost
0.017725
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
207
100.00%
Dialogue to Total Word Ratio
Ratio: 9.66%, Deviation: 0.34%
neededClean
false
wordsTotal
207
wordsDialogue
20
98.8137%