NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K9M7EX70DHQZNSPN4HHG6J
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 43s
Cost:
$0.035074
Provider:
Phala
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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
Molly unfolded a crinkly napkin map of the bouncy castle while Bill squeezed into a clown suit three sizes too small. The van smelled of burnt rubber and discount frosting. She tapped the gift table scribbled in crayon. "Twenty kids, one piƱata, zero guards." Bill's nose honked as he reached for a balloon animal. "And who's the clown?" he asked. Molly tossed him the oversized shoes. "You're the clown." He stared at her. "I hate you." She ignored him and said, "No crying, no mercy." She checked the van's rearview mirror and adjusted her party hat. The hat had a unicorn horn and a hidden camera. It was very ridiculous. The plan was simple: during the magic show, the parents would clap at a rabbit while Bill fell into the ball pit and pretended to drown. Molly would load forty presents into the cake cart and roll them out the back. Nothing could go wrong, except Bill's shoes squeaked like dental drills and the balloon giraffe had a slow leak. Still, they had pulled off riskier jobs, like the time they stole a bouncy castle with only a leaf blower and a forged safety inspection. This would be easy. Probably.
created_at
"2026-09-03T09:29:31.371Z"
9/3/2026, 9:29:31 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1039
moderation_latency
(null)
generation_time
102818
tokens_prompt
75
tokens_completion
7533
native_tokens_prompt
146
native_tokens_completion
7996
native_tokens_completion_images
(null)
native_tokens_reasoning
7735
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
0.03507426
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788427771-zzpeI4Q2ZgDm22VHlfwA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788427771-EPoRz1cHQWJsJ9fCJuQc"
upstream_id
"req_4704b6b9c29b735b6e6b55a9101229a3"
provider_responses
0
endpoint_id
"bb1fb528-2000-460c-a65e-b82dc347c019"
id
"req_4704b6b9c29b735b6e6b55a9101229a3"
is_byok
false
latency
396
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Phala"
status
200
total_cost
0.03507426
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Phala"
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: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%