NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KD1496Z17MS61JWQCJ6MK1
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 25s
Cost:
$0.025455
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 spread the crayon-drawn map across the sticky diner table and tapped a frosting-smeared corner. Bill leaned in, squinting at the balloon-shaped X marking the bouncy castle. Outside, rain streaked the window, but inside his coat pocket he felt the familiar weight of a gift bag guillotine. He bit the end of a licorice whip and nodded slowly. "Cut the piƱata string?" he asked. "Too loud. The ball pit." Bill smiled and folded the map into a paper crown. She had a point; the parents would be too busy managing sugar highs and musical chairs to notice two extra party clowns slipping past the snack table. The real trick was getting back out before the birthday boy unwrapped his shiny new bicycle, because the moment that wrapping paper tore, every adult would be watching. They ordered two coffees and studied the exit route past the face-painting station. Molly pocketed a handful of sugar packets and drew a second path through the gift table. "So we go in as clowns?" "No, as gift wrappers, obviously." Molly dropped a five-dollar bill on the table and grinned. Outside, a birthday clown sneezed into his elbow beside a rusted van. The heist was on.
created_at
"2026-09-03T10:28:59.831Z"
9/3/2026, 10:28:59 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
786
moderation_latency
(null)
generation_time
84436
tokens_prompt
75
tokens_completion
5437
native_tokens_prompt
146
native_tokens_completion
5828
native_tokens_completion_images
(null)
native_tokens_reasoning
5565
native_tokens_cached
128
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
0.02545538
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788431339-cPXyFRVeLZYxvjNMecR7"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788431339-85zUWDlKeWVPVXxnJV09"
upstream_id
"req_c3715b7f76e2614732ef5c8730025f30"
provider_responses
0
endpoint_id
"bb1fb528-2000-460c-a65e-b82dc347c019"
id
"req_c3715b7f76e2614732ef5c8730025f30"
is_byok
false
latency
506
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Phala"
status
200
total_cost
0.02545538
cache_discount
0.0001664
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: 9.76%, Deviation: 0.24%
neededClean
false
wordsTotal
205
wordsDialogue
20
100.0000%