NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2GVZ78VFDJRSRSV1DCMSMZ
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.7s
Cost:
$0.000108
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
21.6892%
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
“You’re telling me we have to get past a bouncy castle?” Bill whispered, peering through the hedge. Molly adjusted her fake clown nose. “Not just a bouncy castle. That one has a slide. And face painters.” “Face painters aren’t security,” he hissed. “They’re witnesses. And the magician does balloon animals. Doves get spooked.” She pointed. “See the piñata? It’s a decoy. The real presents are under the table with the juice boxes.” Bill scratched his balaclava. “So what’s the plan? I distract the pony ride, you grab the loot?” “Better. We’re both party entertainers. I do glitter tattoos. You’re the stilt-walker.” “I can’t walk on stilts.” “You don’t need to. You just collapse. Causes a commotion. While everyone rushes to help, I swap the gift bags with these.” She patted an identical sack filled with rocks. Bill stared. “Rocks. You brought rocks to a kid’s party.” “Weighed them myself. One point two kilos of shame, perfectly balanced.” He sighed. “What about the birthday kid?” “She’s three. She’ll cry for thirty seconds, then there’s cake.” Molly grinned. “Ready?” “I’m not ready.” “Great. You lead.”
created_at
"2026-04-25T14:32:01.518Z"
4/25/2026, 2:32:01 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
595
moderation_latency
(null)
generation_time
5600
tokens_prompt
77
tokens_completion
391
native_tokens_prompt
67
native_tokens_completion
351
native_tokens_completion_images
(null)
native_tokens_reasoning
52
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"
usage
0.00010766
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"3688ccf8-5ffc-4645-ad42-837e4a71f401"
is_byok
false
latency
287
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777127521-mRwegeppo070bnJV8ICX"
session_id
(null)
api_type
"completions"
id
"gen-1777127521-jBgfotL8wtrXqYhsnlTO"
upstream_id
"3688ccf8-5ffc-4645-ad42-837e4a71f401"
total_cost
0.00010766
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
183
0.00%
Dialogue to Total Word Ratio
Ratio: 81.52%, Deviation: 31.52%
neededClean
false
wordsTotal
184
wordsDialogue
150
21.6892%