NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFJ4WGDG3593T5ZQAGX55MB
Run Details
Model:
Qwen 3.5 9B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 43s
Cost:
$0.002327
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9919%
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
The vinegar-scented wind danced around the suburban cul-de-sac, carrying the faint aroma of sugar-syrup and anticipation. Molly adjusted her face paint, glitter smeared across her nose like a tragic clown. Beside her, Bill stared at the colorful bunting like it held encrypted certificates. He twisted a toothpick in his knuckles, assessing the specific risk of matte silver. “They’re all plastic cakes,” she whispered, wiping a smudge of frosting off her cheek. “No, gold glitter tins,” Bill corrected, checking his watch near his pacifier. Molly snatched a balloon and squeezed it into her large leather jacket. She felt responsible for the crime. Bill felt lighter than insured property. The chaos of sugar crashes awaited them there. Sixty-four presents lay in the backyard. They’d need zip ties and extreme patience. The mother wouldn’t mind if they looked very busy. “When do we start?” Bill asked, eyeing the garden hose. “Noon,” Molly replied, tasting the air like a trout. “Too cold,” Bill yawned, rubbing eyes while hiding plastic. “Then we wait,” Molly sighed, whispering slowly. Bill said, “Yes now.” Bill nudged the fence post with a dirty iron bar. He clicked the switch on his bag. The sun beat down slowly. The job was simple.
created_at
"2026-03-11T23:01:42.552Z"
3/11/2026, 11:01:42 PM
model
"qwen/qwen3.5-9b-20260310"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
245
moderation_latency
(null)
generation_time
222524
tokens_prompt
77
tokens_completion
11572
native_tokens_prompt
76
native_tokens_completion
15464
native_tokens_completion_images
(null)
native_tokens_reasoning
11239
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
0.0023272
router
(null)
provider_responses
0
endpoint_id
"00d506d9-a5e9-4382-a2b9-d54732365594"
id
"oagonj8-6Ng1vN-9dae2ebd11a10c40"
is_byok
false
latency
245
model_permaslug
"qwen/qwen3.5-9b-20260310"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773270102-4AurV6mj5wb6hXLsaaIc"
upstream_id
"oagonj8-6Ng1vN-9dae2ebd11a10c40"
total_cost
0.0023272
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
100.00%
Dialogue to Total Word Ratio
Ratio: 9.66%, Deviation: 0.34%
neededClean
false
wordsTotal
207
wordsDialogue
20
99.9919%