NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2FAGWC6WT285J29SPB94Y4
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.9s
Cost:
$0.000089
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8722%
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 helium tank wheezed like a dying accordion as Molly cinched the strap of her purple inflatable T-Rex costume. “Bill, for the last time, a clown will not make for a smoother getaway if you’re sweating through the makeup.” Bill, already half-encased in a lopsided blue elephant suit with a trunk that flopped sadly, glared at her through the eyehole. “This is method,” he grumbled, adjusting a unicorn horn that had been Velcroed onto his head. “We need to blend. Children trust a clown.” Molly snorted, the sound muffled by the dinosaur’s snout. “You look like a drunk beekeeper who fell into a craft store.” He waved a flipper in frustration. “We’ve got six minutes until the parents drop them off for the Pin the Tail on the Donkey massacre. The loot is under the bouncy castle.” Molly flexed her claws. “And exit strategy?” Bill pointed a trunk toward the fence. “Through the hydrangeas, then we hitch the stolen wagon to my cousin’s dog.” There was a long pause. “His name is Pebbles. He’s a pug.” Molly’s T-Rex head wobbled as she sighed. “I’m already the dinosaur. Please don’t make me also be the straight man.”
created_at
"2026-04-25T14:05:01.2Z"
4/25/2026, 2:05:01 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
537
moderation_latency
(null)
generation_time
4865
tokens_prompt
77
tokens_completion
302
native_tokens_prompt
67
native_tokens_completion
284
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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"
usage
0.0000889
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"c43d30a8-fcc3-4bb3-8e04-1ec1583c2e30"
is_byok
false
latency
286
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777125901-y8joIsr26pJ3czoUC5F2"
session_id
(null)
api_type
"completions"
id
"gen-1777125901-3Ks09ohFkdqOhmosRzow"
upstream_id
"c43d30a8-fcc3-4bb3-8e04-1ec1583c2e30"
total_cost
0.0000889
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
0.00%
Dialogue to Total Word Ratio
Ratio: 53.30%, Deviation: 43.30%
neededClean
false
wordsTotal
197
wordsDialogue
105
49.8722%