NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2FW8H7JTHRQQ58ERFSZGH6
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
12.9s
Cost:
$0.000490
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
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
Molly squinted at the inflatable bouncy castle. “The piñata’s a distraction. We hit the gift table during the candy scramble.” Bill adjusted his clip-on rainbow suspenders. “Clown shoes squeak. I’ll alert every toddler within a six-foot radius.” “That’s why you’re the silent type, remember? Honk a horn twice if you spot the birthday boy’s mom.” She handed him a paper party hat. “Twenty-seven presents, Bill. I counted through the fence. One’s definitely a bike.” “I can’t ride a bike with a glitter princess frame.” He jammed the hat over his bald head. “It’s about dignity.” “It’s about resale value. You’ll pedal with your knees up like a praying mantis and you’ll love it.” Molly smeared cupcake frosting on her nose for camouflage. “Now, what’s our exit code for an angry magician?” “Balloon animal emergency.” Bill sighed, testing a squeaky flower on his lapel. “I should’ve taken that bank job. Alarms are less humiliating than bunny ears.” “Banks don’t have chocolate fountains. Focus.” She patted his foam clown nose. “We waddle in, we wrap gifts in the bunting, we waddle out as a two-man birthday present mummy. Beautiful.” “The piñata is shaped like a dinosaur.” “Then we pray for herbivores.”
created_at
"2026-04-25T14:14:42.476Z"
4/25/2026, 2:14:42 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1049
moderation_latency
(null)
generation_time
12808
tokens_prompt
77
tokens_completion
596
native_tokens_prompt
67
native_tokens_completion
530
native_tokens_completion_images
(null)
native_tokens_reasoning
215
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
0.000490245
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"9ca678b4-0615-4ff8-8735-4bf430eef869"
is_byok
false
latency
339
model_permaslug
"deepseek/deepseek-v4-pro-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777126482-ugBDjPcHYccOK7dHzGK7"
session_id
(null)
api_type
"completions"
id
"gen-1777126482-uKcv0LH9v7oK3dqk1RHv"
upstream_id
"9ca678b4-0615-4ff8-8735-4bf430eef869"
total_cost
0.000490245
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
199
0.00%
Dialogue to Total Word Ratio
Ratio: 73.76%, Deviation: 23.76%
neededClean
false
wordsTotal
202
wordsDialogue
149
49.9995%