NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2EYFSE0A4NQ9DSJ9GFM4FF
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
26.8s
Cost:
$0.001544
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
47.9934%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 cake is an inflatable,” Molly said, tapping the blueprint with a sparkly marker. “Twelve feet of air-filled icing. It’s our way in.” Bill squinted. “You want me to hide inside a bouncy castle’s diabetic cousin?” “You’ll wear a party hat and a smile. The giggling will mask your grunting.” “My grunting has been professionally silenced,” Bill said, offended. “But Ihr heavy lifting, where’s your slice of the humiliation?” Molly smirked. “I’m the emergency clown. Honking a nose is my cover for casing the gift table. When the piñata bursts, I deploy a glitter-based smoke screen.” “You’d weaponise arts and crafts?” “It’s non-toxic and biodegradable chaos, Bill. A tactical rainbow.” Bill sighed, eyeing a sketch of a juice-box-shaped safe-cracker. “And the bouncy castle is just a decoy? Its primary function is bounce.” “Precisely. The children will be experiencing vertical joy while we horizontally redistribute their presents into a sack marked ‘Clown College Tuition.’ The birthday boy is turning five, his security is lax, his motor skills are still developing. We’re not stealing, we’re correcting a gift surplus.” “A surplus that’s contained in a sack.” “A *festive* sack, Bill. We’re monsters with a theme. Now, can you fit inside the cake or do I need to butter you up?”
created_at
"2026-04-25T13:58:37.632Z"
4/25/2026, 1:58:37 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9123
moderation_latency
(null)
generation_time
15931
tokens_prompt
77
tokens_completion
369
native_tokens_prompt
67
native_tokens_completion
319
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.0015443
router
(null)
provider_responses
0
endpoint_id
"13bda129-f8a6-4a60-b1db-98082e5f7ccd"
id
"ogZVofy-6z2FuN-9f1ddd15412458f1"
is_byok
false
latency
9123
model_permaslug
"deepseek/deepseek-v4-pro-20260423"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777125517-eW8tjfvcpNsumJ4mjxQu"
session_id
(null)
api_type
"completions"
id
"gen-1777125517-uRTVK2D6QpDzzR7YJGrG"
upstream_id
"ogZVofy-6z2FuN-9f1ddd15412458f1"
total_cost
0.0015443
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
0.00%
Dialogue to Total Word Ratio
Ratio: 86.92%, Deviation: 36.92%
neededClean
false
wordsTotal
214
wordsDialogue
186
47.9934%