NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-20-01M5C6Q42Q9NCYCTBPSQGY0G87
Run Details
Model:
DeepSeek V4.1 Flash 1017 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.9s
Cost:
$0.000198
Provider:
InferenceNet
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
94.46%
Dialogue to Total Word Ratio
(details)
48.2351%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"So the clown's our inside man?" Bill whispered, adjusting his tiny party hat. "He's not our inside man, he's our distraction," Molly hissed. "He juggles, we snatch." "Right, but what about the piƱata? That's full of candy, not cash." "We're not after candy, Bill. We're after the presents. The big box with the bow." "The one that says 'For Tommy, happy fifth birthday, love Grandma'?" "That's the one. Inside is a limited-edition gold coin set. Grandma's loaded." "And the kids?" "They'll be blindfolded for pin the tail on the donkey. We slip in during the chorus of Happy Birthday." "What if someone sees us?" "They'll see two guys in bear costumes carrying a sack. Who questions a bear at a party?" "The birthday boy might." "He's four. He'll think we're animatronics." "And the parents?" "They'll be three mimosas deep by noon. We're fine." "Okay. But if the clown starts crying again, I'm out." "Deal. Now let's practice our bear walk." "This is the weirdest heist we've ever done." "You said that about the petting zoo."
created_at
"2026-10-20T08:26:46.749Z"
10/20/2026, 8:26:46 AM
model
"deepseek/deepseek-v4.1-flash-20261017"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
151
moderation_latency
(null)
generation_time
3910
tokens_prompt
75
tokens_completion
379
native_tokens_prompt
67
native_tokens_completion
386
native_tokens_completion_images
(null)
native_tokens_reasoning
113
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
0.00019836
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1792484806-cpyVpM7Bx34D8s7bBeOj"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1792484806-t9x2ZXAB1niUiBlD7sdk"
upstream_id
"gv2_ISxBRdUgUe5wfoPpan2Yy"
provider_responses
0
endpoint_id
"4231aea9-73af-4a2f-bd14-660b1d8b13b2"
id
"gv2_ISxBRdUgUe5wfoPpan2Yy"
is_byok
false
latency
151
model_permaslug
"deepseek/deepseek-v4.1-flash-20261017"
provider_name
"InferenceNet"
status
200
total_cost
0.00019836
cache_discount
(null)
upstream_inference_cost
0
provider_name
"InferenceNet"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
2.01%
Matches word count
n/a
neededClean
false
words
175
94.46%
Dialogue to Total Word Ratio
Ratio: 94.89%, Deviation: 4.89%
neededClean
false
wordsTotal
176
wordsDialogue
167
48.2351%