NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DRYRARKV0C8S2DXQECPWQ
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
25.8s
Cost:
$0.004050
Provider:
DeepSeek
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
Molly peered through the inflatable castle’s mesh. "Clown is perimeter. Piñata is vault. Presents are ours by noon." Bill adjusted his party hat. "I still say we should have RSVP’d." "You’re a balloon animal. Act balloon-ish." "Balloons don’t carry bolt cutters." "Hide them in the gift bag." "It says Happy Birthday, Chloe." "Perfect. Nobody suspects the birthday bag." They watched a toddler guard a pile of wrapped boxes with terrifying focus. "What about the kids, Molly?" Bill asked. "We distract them with cake." "And the parents?" "Entertainment agency." "Are we really?" "We are now." Bill sighed. "Molly, this is wrong." "It’s a heist, Bill. Morality is a party favor." Behind them, a clown folded balloon swords. A banner promised cake and chaos. Bill’s hands trembled inside his oversized gloves. Somewhere, a pinata swayed like a hanged piñata. Molly produced a clipboard labeled Party Logistics. The toddler narrowed his eyes. Kazoo shrieked. Bill considered fleeing, the presents glittered under the fairy lights like cheap, beautiful treasure. A mother approached. Molly smiled. "Hello! We’re collecting presents for the charity raffle." The mother blinked. "What raffle?" "The one we’re about to invent," Bill whispered. Molly stepped on his foot. "The surprise raffle one."
created_at
"2026-09-10T10:28:20.367Z"
9/10/2026, 10:28:20 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
804
moderation_latency
(null)
generation_time
25801
tokens_prompt
75
tokens_completion
5952
native_tokens_prompt
93
native_tokens_completion
6727
native_tokens_completion_images
(null)
native_tokens_reasoning
6413
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
0.00405015
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789036100-Q9pRKEBfNmwDgRQfwlxV"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789036100-i8TsazQat8GdGPnuQezm"
upstream_id
"a6eb617e-224f-4074-b9fe-d63a5de4e5b7"
provider_responses
0
endpoint_id
"fd104bc8-535a-4d31-a847-a8e402e86a02"
id
"a6eb617e-224f-4074-b9fe-d63a5de4e5b7"
is_byok
false
latency
345
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"DeepSeek"
status
200
total_cost
0.00405015
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
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%