NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KCGDR0N0JTDCYQSRQJM1HV
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 40s
Cost:
$0.028586
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 crouched behind the bouncy castle, licking stolen frosting from her thumb while Bill counted the gift table through joke-shop binoculars. This was not their usual bank job, but the take was cleaner. Molly had spent three days casing the bouncy castle's blind spot. Bill adjusted his squeaky party hat. It squeaked. Every movement sounded like a tiny rubber chicken confessing to a crime. The clown turned slowly. Bill squeaked again. The birthday boy howled for more juice. The clown honked a rubber horn, and Molly slipped a roll of wrapping paper from her coat. Bill raised an eyebrow. "Wait, you want us to wrap ourselves?" Molly nodded and passed him an end. "Biggest gift they'll never expect." Bill wound the paper around his waist, checked the sightlines, and adjusted his party hat as it tilted over one eye. Molly ducked behind the juice boxes, reappearing with a bow stuck to her forehead. "Trust me." She spun her finger. "We waddle in, grab, waddle out." Bill obeyed, turning until the paper covered his arms. They waddled toward the glittering present mountain, a single festive beast with four feet, two slightly hungover faces, and a trail of tape unraveling behind them.
created_at
"2026-09-03T10:19:52.459Z"
9/3/2026, 10:19:52 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1151
moderation_latency
(null)
generation_time
100407
tokens_prompt
75
tokens_completion
6251
native_tokens_prompt
146
native_tokens_completion
6546
native_tokens_completion_images
(null)
native_tokens_reasoning
6278
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
0.02858586
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430792-rr1uD3pihPW206LrlPQX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430792-FTSMjQqgrL9SDvAMeiyJ"
upstream_id
"req_4160aebe32fde9678dbff232928aeaeb"
provider_responses
0
endpoint_id
"bb1fb528-2000-460c-a65e-b82dc347c019"
id
"req_4160aebe32fde9678dbff232928aeaeb"
is_byok
false
latency
403
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Phala"
status
200
total_cost
0.02858586
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: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
100.0000%