NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K9NZ6EGEGNDT40X8137FA4
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.5s
Cost:
$0.000101
Provider:
Wafer
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
61.5841%
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
"Okay, run it by me again, Bill. We're robbing a bouncy castle?" "We're robbing the presents, Molly, not the castle. The castle is just the venue." "Right. And the target demographic? Five-year-olds." "Six to nine, actually. The parents'll be drunk near the punch bowl. The kids'll be hyped on cake. Easy pickings." "So our grand criminal plan is to stick up a bunch of toddlers for a gift bag and a plush unicorn?" "It's a majestic plush unicorn. Limited edition. It's worth serious money on the collector's market, believe it or not." "I find that very hard to believe." "I've seen it. Now, listen. I'll cause a distraction by 'magically' producing a live dove from my sleeve." "You don't have a dove." "I have a bag of flour and a rubber chicken. The outcome is the same. Chaos. While the little monsters are crying, you move in on the present table." "I'm not climbing over a table. My back hurts." "Then you'll crawl under it. Jesus, Molly, it's a snatch and grab." "But there's confetti everywhere. It'll get in my hair." "I'll give you a dollar." "Fifty." "Four dollars and that's final." "You're a cheap boss, Bill. A real criminal mastermind." "Stop complaining and start stretching. The party opens at two."
created_at
"2026-09-03T09:30:28.445Z"
9/3/2026, 9:30:28 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3544
moderation_latency
(null)
generation_time
8142
tokens_prompt
75
tokens_completion
387
native_tokens_prompt
89
native_tokens_completion
370
native_tokens_completion_images
(null)
native_tokens_reasoning
66
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
0.0001014
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788427828-78QCTLSBlp21xq7mLdzB"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788427828-SUOfJJMDILs9CdH9IcjE"
upstream_id
"c6a3edc281314f38a1a1bfeb26893a9a"
provider_responses
0
endpoint_id
"47a93b18-a9c6-485b-9a47-2afb6ca790dc"
is_byok
false
latency
62
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"BaseTen"
status
429
1
endpoint_id
"604391ba-7c17-4f8b-8a18-b38c5b45ac52"
is_byok
false
latency
2264
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Together"
status
429
2
endpoint_id
"4d5286fc-8f37-40c2-a518-e1ae100d45fc"
id
"c6a3edc281314f38a1a1bfeb26893a9a"
is_byok
false
latency
3538
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Wafer"
status
200
total_cost
0.0001014
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Wafer"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
211
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
213
wordsDialogue
213
61.5841%