NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KCFZ39NN85Q9VWX93FHXPN
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
20.7s
Cost:
$0.000295
Provider:
Reka
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
98.58%
Dialogue to Total Word Ratio
(details)
89.9265%
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
Molly flattened herself against the hedge, binoculars trained on the bouncy castle. "Bill, the target is a five-year-old's birthday party. There's a clown." Bill squinted. "A clown? That's a complication." "Not the clown. The presents. Stacked like a fortress of wrapping paper by the picnic table." "Right. So we waltz in, grab the haul, and out. Easy." "Waltz? Bill, there's a magician doing balloon animals. We need a distraction." "Like what? I could fake a seizure." "Last time you did that, a nun called an ambulance." "Fine. You do the seizure. I'll grab the gifts." "The birthday girl is wearing a tiara and screaming about a unicorn piƱata. She's got the energy of a tiny dictator." "Perfect. We'll blend in. You cry, I'll say I'm your husband, we're here for our 'nephew'." "We don't have a nephew." "We'll invent one. Kevin. Kevin loves dinosaurs." "Bill, the parents are watching us. We're the only adults without juice boxes." "Then grab a juice box. And a cupcake. Act festive." "This is insane." "Insane is stealing a car. This is stealing presents from children. That's just capitalism." "Fine. But if I end up doing the chicken dance, I'm blaming you." "Deal. Now, on three. One... two..." "Wait, is that the clown crying?" "Probably. Let's move."
created_at
"2026-09-03T10:19:37.469Z"
9/3/2026, 10:19:37 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2410
moderation_latency
(null)
generation_time
18826
tokens_prompt
75
tokens_completion
432
native_tokens_prompt
146
native_tokens_completion
422
native_tokens_completion_images
(null)
native_tokens_reasoning
101
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
0.00029458
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430777-JMrRdAHsxPkuK2LxpFAY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430777-2Xvgiwun4mZ8FlFBbJe9"
upstream_id
"b08501e8e5614ca9844cf667d0686509"
provider_responses
0
endpoint_id
"562d5188-97d1-49f7-8881-d0e417e31ada"
is_byok
false
latency
48
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Makora"
status
429
1
endpoint_id
"14c4df90-c7af-42ff-99e7-69d62a89e7d5"
is_byok
false
latency
1354
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"AkashML"
status
429
2
endpoint_id
"223c54e7-4db1-4098-980f-47741e7637ab"
is_byok
false
latency
385
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Baidu"
status
429
3
endpoint_id
"ceaae883-4cba-45dd-b986-5cd0e6bf06af"
is_byok
false
latency
47
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"BaseTen"
status
429
4
endpoint_id
"497727f1-91e7-4775-a469-ccdd96e0f0d8"
id
"b08501e8e5614ca9844cf667d0686509"
is_byok
false
latency
2410
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Reka"
status
200
total_cost
0.00029458
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Reka"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
212
98.58%
Dialogue to Total Word Ratio
Ratio: 93.46%, Deviation: 3.46%
neededClean
false
wordsTotal
214
wordsDialogue
200
89.9265%