NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K9PYG55GG679BFPAJAM38B
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3m 34s
Cost:
$0.002310
Provider:
DeepInfra
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 50% 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 party tent sagged like a disappointed balloon, its striped fabric drooping in the oppressive heat. Molly peeked over a hedge, her binoculars fogging up from the humidity. She wiped the lenses on her sleeve. "Twelve kids, three adults, one dog. The target is a pirate princess thing." Bill, tugging at a rubber nose that kept slipping, sighed. "And the loot?" She lowered the binoculars. "Tablets, LEGOs, gift cards. A unicorn piƱata." He grimaced, scratching his stubble. "Unicorns. Smug." "Focus. The magic show starts at 3:30." Bill adjusted his fake mustache, which had begun to peel. "But Kevin? The birthday kid? He's seven. He'll guard those presents like a honey badger." Molly patted her pocket. "We have chloroform." "That's a felony." "Lavender-scented. He naps. We take the gift cards." Bill nodded. "Fine. Skip Grandma's cash envelopes." "Deal. We're thieves, not monsters." Bill pulled on gloves, his mustache wobbling. "Let's go ruin a core memory." Molly grinned, adjusting her ski mask. "Remember the signal: if you see the clown, we abort." "What clown?" "The one from the party store. Terrifying." "Oh no. Not him." Bill's face went pale. He swallowed. The wind died. A deflated balloon rolled past, and he jumped.
created_at
"2026-09-03T09:31:00.502Z"
9/3/2026, 9:31:00 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
503
moderation_latency
(null)
generation_time
214096
tokens_prompt
75
tokens_completion
9467
native_tokens_prompt
67
native_tokens_completion
12804
native_tokens_completion_images
(null)
native_tokens_reasoning
9157
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
0.00231008
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788427860-9kLMDodw7Q3ZXOIabXWU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788427860-9gjnb1idMuRjZ3oGS9IZ"
upstream_id
"chatcmpl-RRE7ncvXtshhRzbaN4py9HWp"
provider_responses
0
endpoint_id
"c1980fff-0a72-4bce-8d62-a7d3fc582200"
id
"chatcmpl-RRE7ncvXtshhRzbaN4py9HWp"
is_byok
false
latency
60
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"DeepInfra"
status
200
total_cost
0.00231008
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
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: 50.25%, Deviation: 0.25%
neededClean
false
wordsTotal
201
wordsDialogue
101
100.0000%