NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2FN0HXSGFQTZNT4M03GDRS
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.8s
Cost:
$0.000110
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9920%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
The helium tank sat between them like a bloated silver nun. Bill traced the party flyer with a greasy finger. “The bounce castle is a decoy,” he whispered. “The real haul is in the loot bags.” Molly adjusted her fake glasses, which had no lenses. “And the smoke machine?” “Clown entrances. Classic misdirection.” He tapped the venue map. “We go in as magicians. You swallow the keys to the minivan. I distract with a rubber chicken.” She squinted at the napkin schematic. “The birthday girl’s mother has the presents under the picnic table. She’s built like a bouncer, Bill.” “That’s why we have the fart spray.” A long pause. Molly picked at a hangnail. “We are robbing five-year-olds.” “Morally dubious,” Bill agreed. “Financially sound. They get macaroni art and feelings. We get gift cards and action figures.” “And the glitter bomb in my pocket?” “Emergency escape. We look like disco lepers. They’ll pity us.” Molly sighed, popped her back, and stood. “Fine. But I am not eating the key this time. Last party I passed it in the bathroom for three hours.” Bill grinned. “That’s why you’re the decoy. Now, remember: if anyone asks, our names are Sparkles and The Amazing Moist.”
created_at
"2026-04-25T14:10:44.929Z"
4/25/2026, 2:10:44 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
599
moderation_latency
(null)
generation_time
5660
tokens_prompt
77
tokens_completion
402
native_tokens_prompt
67
native_tokens_completion
360
native_tokens_completion_images
(null)
native_tokens_reasoning
61
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
0.00011018
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"606ad965-0c7c-4431-a137-3f70a1bfdf3b"
is_byok
false
latency
265
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-1777126244-xFdYuoGzT56akg50TYv0"
session_id
(null)
api_type
"completions"
id
"gen-1777126244-OjSTvsgSir8uMl5MQwUR"
upstream_id
"606ad965-0c7c-4431-a137-3f70a1bfdf3b"
total_cost
0.00011018
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
0.00%
Dialogue to Total Word Ratio
Ratio: 70.10%, Deviation: 60.10%
neededClean
false
wordsTotal
204
wordsDialogue
143
49.9920%