NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KCGPCJ9F50759M8XQ2Y6QG
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 40s
Cost:
$0.046466
Provider:
Sail Research
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9980%
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 crouched behind a penguin-shaped hedge and pointed at the inflatable castle wobbling under a dozen sugar-crazed children and a loose banner. "I'm telling you, Bill, the cake is our way in." Bill squinted through his binoculars and adjusted the focus. "It's a sheet cake. I can't hide in it." She sighed and pinched the bridge of her nose, leaving a tiny orange stain. "Not you. The presents. We swap the gift table with decoys." Bill scratched his neck, eyeing the clown twisting balloon animals into a giraffe. "Then what, waltz out with thirty boxes?" "Exactly. Everyone's too busy whacking a piñata." Bill frowned at the inflatable slide. "There's a clown." Molly shrugged and stole a cheese puff from a tray. "So we bring balloons." Bill considered, tapping his chin. "Do we sing?" "We hum. Low. From the buffet." He nodded slowly as a toddler shrieked past. "What about the bouncy castle?" "Diversion. You trip the generator." Bill grinned. "Grab the wagon and your cool uncle stance." Molly patted his arm. "It's a heist, Bill. We blend." Bill picked up a party hat. "I'm not wearing this." He sighed. "Fine, but if I get glitter on my picks again—" "No promises."
created_at
"2026-09-03T10:20:01.315Z"
9/3/2026, 10:20:01 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
864
moderation_latency
(null)
generation_time
99673
tokens_prompt
75
tokens_completion
9544
native_tokens_prompt
146
native_tokens_completion
11732
native_tokens_completion_images
(null)
native_tokens_reasoning
11433
native_tokens_cached
145
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
0.04646642
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430801-HvkC1RWY66p4EGQjLAd6"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430801-y9pfgzCBeebb4qONhz2s"
upstream_id
"asapreq_0435e7d2fde591b6771d0d8364395735"
provider_responses
0
endpoint_id
"6811c06b-8624-4796-ad6e-807e33b97ae6"
id
"asapreq_0435e7d2fde591b6771d0d8364395735"
is_byok
false
latency
864
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Sail Research"
status
200
total_cost
0.04646642
cache_discount
0.00018502
upstream_inference_cost
0
provider_name
"Sail Research"
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
201
100.00%
Dialogue to Total Word Ratio
Ratio: 49.26%, Deviation: 0.74%
neededClean
false
wordsTotal
203
wordsDialogue
100
99.9980%