NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KB55Q7BR1VCV6SNBA1NXH0
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 30s
Cost:
$0.037734
Provider:
Sail Research
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9997%
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 spread the birthday party blueprint across the sticky card table. "The gift table sits beside the bouncy castle, correct?" Bill nodded, peeling a leftover sticker from his sleeve. "Yeah, but a clown guards it. Hired entertainment." Molly smirked, twirling a party horn between her fingers. "I can out-clown a clown." Bill shook his head slowly, remembering the swan. "You once got trapped in a balloon animal." "That was a swan, and it was aggressive," she said. "Focus. We need to enter during the piƱata frenzy at exactly two-fifteen." Bill pulled a red wagon from behind the hedge. "I reinforced the wheels for high-speed extraction." Molly raised an eyebrow and tapped the teddy bear sticker. "It still has a teddy bear sticker." "That's my emotional support decoy," he whispered. She unfolded a map and pointed to the bubble machine. "We load the presents here, then escape through the bubble machine." Bill frowned, scratching his chin through his rainbow wig. "Bubbles reduce visibility." "Exactly. It's perfect." Bill hesitated, watching a toddler parade roll past. "What about the children?" Molly rattled a bag of chocolate coins. "We toss these and run." Bill grinned, adjusting his floppy shoes. "I love working with professionals."
created_at
"2026-09-03T09:56:15.223Z"
9/3/2026, 9:56:15 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
603
moderation_latency
(null)
generation_time
89823
tokens_prompt
75
tokens_completion
8286
native_tokens_prompt
146
native_tokens_completion
9480
native_tokens_completion_images
(null)
native_tokens_reasoning
9199
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
0.03773352
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788429375-I98NflZ723zPb9DKU0Pp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788429375-dWbdjzRyRN9HaTkz9d60"
upstream_id
"asapreq_4cedb266f685e0e17f89637933de346f"
provider_responses
0
endpoint_id
"6811c06b-8624-4796-ad6e-807e33b97ae6"
id
"asapreq_4cedb266f685e0e17f89637933de346f"
is_byok
false
latency
603
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Sail Research"
status
200
total_cost
0.03773352
cache_discount
(null)
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
200
100.00%
Dialogue to Total Word Ratio
Ratio: 50.50%, Deviation: 0.50%
neededClean
false
wordsTotal
202
wordsDialogue
102
99.9997%