NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KB78870WJV84DMM63649N9
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.5s
Cost:
$0.000083
Provider:
Relace
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
97.98%
Dialogue to Total Word Ratio
(details)
52.0372%
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 target is a birthday party. Ages four to seven,” Molly said, peering through binoculars from the parked van. “Four to seven. That’s the demographic. High-value loot. Unwrapped, too. They do the present pile on a plastic table,” Bill replied, chewing a pen. “And the parents? They’ll be watching like hawks.” “They’ll be drunk on fruit punch and small talk. The real security is a clown. Goes by ‘Bubbles.’ Does balloon animals. Also has a taser.” “A taser-wielding clown? That’s your intel?” “I saw him use it on a piñata that wouldn’t break. He’s a professional.” “Okay. So we go in as... what? Another clown?” “No. Too risky. We go in as the birthday girl’s divorced uncle and his new girlfriend. We bring a gift. It’s a decoy. Inside is a motorized fart machine. When it goes off, chaos.” “You want to cause a flatulence panic at a kids’ party? Bill, that’s genius.” “Then while Bubbles is doing CPR on a balloon poodle, we grab the gift bags. Every single one. Plus the cake.” “We’re stealing cake?” “It’s a smash cake. Worth forty dollars. And it has a tiny race car on top. We need that.” “So we’re targeting children’s presents and a cake with a toy car.” “It’s a heist, Molly. Not a charity event.” “Fine. But I’m keeping the car.”
created_at
"2026-09-03T09:57:23.376Z"
9/3/2026, 9:57:23 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
635
moderation_latency
(null)
generation_time
10596
tokens_prompt
75
tokens_completion
424
native_tokens_prompt
146
native_tokens_completion
408
native_tokens_completion_images
(null)
native_tokens_reasoning
65
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
0.00008293
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788429443-v2q8W0ufpgoA36G7sLLB"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788429443-Tv0GGfjoNvmr0wWdWF9b"
upstream_id
"55d11e7bb612486ca6fef9075966dcaa"
provider_responses
0
endpoint_id
"cb029acf-a84f-4280-8103-909d269e1e5f"
is_byok
false
latency
287
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"DigitalOcean"
status
429
1
endpoint_id
"223c54e7-4db1-4098-980f-47741e7637ab"
is_byok
false
latency
358
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Baidu"
status
429
2
endpoint_id
"14c4df90-c7af-42ff-99e7-69d62a89e7d5"
is_byok
false
latency
1185
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"AkashML"
status
429
3
endpoint_id
"57c1bfab-049c-4d6a-ab34-ac1007a6043b"
id
"55d11e7bb612486ca6fef9075966dcaa"
is_byok
false
latency
635
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Relace"
status
200
total_cost
0.00008293
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Relace"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
6.09%
Matches word count
n/a
neededClean
false
words
223
97.98%
Dialogue to Total Word Ratio
Ratio: 93.78%, Deviation: 3.78%
neededClean
false
wordsTotal
225
wordsDialogue
211
52.0372%