NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KC7SD5M2G1Q27Y7ZBQRDGM
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 36s
Cost:
$0.028442
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 crayon-drawn map of the bouncy castle perimeter, her finger tracing the juice-box stain that marked the present table. Bill nodded as if it were blueprints for the Federal Reserve. "The piƱata guy is our mark," she whispered. "We strike during musical chairs." Bill frowned. "What about the clown?" "Trust me. Balloon animal distraction," Molly said. They crouched behind an old hedge shaped like a giraffe, watching toddlers waddle past with frosting-caked fists. Bill tightened the strap of his oversized duffel bag, which contained a small roll of tape, a pair of safety scissors, and a single juice box for courage. The plan was deceptively simple: wait for the birthday boy to blow out his candles, then hit the gift table while the adults were blinded by camera flashes and sentimental tears. Molly would unzip the loot sacks; Bill would stuff stuffed dinosaurs and Legos into the bag. The hardest part, they agreed, would be resisting the snack table. Bill insisted on wearing a party hat as a disguise. Molly insisted it made him more conspicuous. They compromised on two matching hats. In the distance, a nearby ice cream truck played a very sinister, deeply off-key tune softly.
created_at
"2026-09-03T10:15:09.491Z"
9/3/2026, 10:15:09 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1436
moderation_latency
(null)
generation_time
95685
tokens_prompt
75
tokens_completion
6416
native_tokens_prompt
146
native_tokens_completion
6513
native_tokens_completion_images
(null)
native_tokens_reasoning
6254
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
0.02844198
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430509-KeHvKcf53rOxliFLZxD8"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430509-FGGwUhAZetQdTBHCyS2N"
upstream_id
"req_62455ddd73f908f32c6e2ea1271236ca"
provider_responses
0
endpoint_id
"bb1fb528-2000-460c-a65e-b82dc347c019"
id
"req_62455ddd73f908f32c6e2ea1271236ca"
is_byok
false
latency
534
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Phala"
status
200
total_cost
0.02844198
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: 9.80%, Deviation: 0.20%
neededClean
false
wordsTotal
204
wordsDialogue
20
100.0000%