NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KCA3WJSNVETKVDVTKNCS3C
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
13.4s
Cost:
$0.009979
Provider:
Sail Research
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.9949%
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 a crinkled birthday map across the sticky table of their van, next to a half-eaten juice box and a stolen party hat. "We hit the bouncy castle at exactly two, when the clown starts balloon animals." Bill squinted at the crayon-drawn schematic, his face serious. "The clown's a wildcard. What if he's one of those mimes?" Molly tapped the present pile photo, leaving a fingerprint on a grinning child's face. "Then we use the distraction. You trip the piƱata string, I'll stuff the gift bags into the stroller." Bill frowned and gestured at his broad shoulders. "I don't fit in a stroller." "Not you. The presents. You'll be the pony." Bill considered this role. "Do I get a tail?" Molly sighed, already regretting the plan. "If it keeps you quiet." She pointed to a side gate on the map. "Cake comes out at two-fifteen. Parents cry, phones go up. We move." Bill nodded slowly, then chewed his lip. "And if a four-year-old spots me?" "Tell her you're the new magician." Bill grinned, revealing a missing molar. "I can't do magic." Molly zipped the duffel bag hard enough to catch his finger. "That's fine. Neither can the clown."
created_at
"2026-09-03T10:16:25.757Z"
9/3/2026, 10:16:25 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
399
moderation_latency
(null)
generation_time
13382
tokens_prompt
75
tokens_completion
2127
native_tokens_prompt
146
native_tokens_completion
2518
native_tokens_completion_images
(null)
native_tokens_reasoning
2231
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
0.00997898
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430585-tGfCK4RoGMG5NoGtk9bI"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430585-6umM2SquSFzL6OJdiL5v"
upstream_id
"asapreq_531146b9d9abf4d4c1275fa55dcd112b"
provider_responses
0
endpoint_id
"6811c06b-8624-4796-ad6e-807e33b97ae6"
id
"asapreq_531146b9d9abf4d4c1275fa55dcd112b"
is_byok
false
latency
399
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Sail Research"
status
200
total_cost
0.00997898
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
199
99.99%
Dialogue to Total Word Ratio
Ratio: 50.98%, Deviation: 0.98%
neededClean
false
wordsTotal
204
wordsDialogue
104
99.9949%