NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M107YR2NJHTJ203Z69Z9W3
Run Details
Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 55s
Cost:
$0.019064
Provider:
Ionstream
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 stood outside the party window, her mask slipping under a cloud of confetti. Bill held a ladder made of stolen cake stands. Inside, kids chanted around a table buried in wrapped packages, each ribbon a tiny promise they had no idea would vanish. Molly said, "Bill, the presents smell of glitter and bad decisions." Bill replied, "Glitter is temporary; greed is permanent. Count every present box first." The moon peeked through balloons, making the backyard look like a crime scene designed by a cheerful intern. Somewhere, a plastic trumpet squeaked. Bill pretended not to hear it. Molly arranged her stolen gloves. The host wore a foil crown. The kids applauded crinkling paper. A dog judged the thieves. Bill winked. The dog did not wink. The plan was simple. Molly would distract the mother with a fake bee. Bill would lift the gift towers into a wagon disguised as a mobile stage. The birthday cake sat on a pedestal like a guilty jewel. If any child asked, Molly claimed to be a magician lost in the backyard. The plan ignored the obvious fact that children remembered everything, especially when it involved cake, confetti, or a stranger with a suspicious wagon.
created_at
"2026-09-03T16:18:02.335Z"
9/3/2026, 4:18:02 PM
model
"qwen/qwen3.8-27b-20260814"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
177
moderation_latency
(null)
generation_time
115066
tokens_prompt
75
tokens_completion
6072
native_tokens_prompt
118
native_tokens_completion
7460
native_tokens_completion_images
(null)
native_tokens_reasoning
7211
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"
service_tier
(null)
usage
0.0190643
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788452282-3ODxb02JzKapFmpiBNeq"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788452282-6GepK91lotmQd4ZCqZUl"
upstream_id
"5b3c9d7893a54b2089301ed9ccf6d0fa"
provider_responses
0
endpoint_id
"360e373e-d445-4de9-ae30-e33d6198715b"
id
"5b3c9d7893a54b2089301ed9ccf6d0fa"
is_byok
false
latency
177
model_permaslug
"qwen/qwen3.8-27b-20260814"
provider_name
"Ionstream"
status
200
total_cost
0.0190643
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Ionstream"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%