NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KAKKY394V0QCJF7KGQR1FE
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
31.0s
Cost:
$0.006976
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
66.12%
Dialogue to Total Word Ratio
(details)
83.0609%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 said, "We hit the bouncy castle entrance at two." Bill whispered, "The clown's making balloon animals by the cake table." "Perfect. I'll wear the Sparkle Princess costume and blend with the entertainers." "You? Sparkle Princess? You hate glitter." "Desperate times. You're on present extraction. The pile's by the pinata, right?" "Yeah, but there's a dozen five-year-olds guarding it with juice boxes." "Juice boxes? We've faced lasers." "These kids bite, Molly. And they cry. Loud." "So we bring a distraction. I'll announce a real unicorn in the backyard." "There's no unicorn." "I'll paint the pony. Bill, focus. Once they stampede, you grab the big boxes first. The one with the robot dinosaur is worth three grand." "How do you know which box?" "I shook it at the gift table. It has a red ribbon and a card that says 'For Timmy, love Grandma.'" "Timmy's grandma has money." "Exactly. Now, exit route?" "Through the ball pit to the kitchen, out the side gate." "What if the birthday boy sees us?" "Then we sing. Kids love singing." "Fine. But if you get glitter in my getaway car, I'm leaving you." "Deal. Let's go steal some childhood joy." "Got it. Let's move now."
created_at
"2026-09-03T09:46:39.958Z"
9/3/2026, 9:46:39 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
200
moderation_latency
(null)
generation_time
30957
tokens_prompt
75
tokens_completion
2167
native_tokens_prompt
146
native_tokens_completion
2610
native_tokens_completion_images
(null)
native_tokens_reasoning
2317
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"
service_tier
(null)
usage
0.0069758
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788428799-JcDgZRTUNiF8sU4WO5ue"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788428799-uHX1aupbPhxrISeZxbnu"
upstream_id
"chatcmpl-RQwW4J93HIqUt2Kkxp3gEOgC"
provider_responses
0
endpoint_id
"a69687f5-7209-4d1d-b4d6-50a9939aa5ce"
id
"chatcmpl-RQwW4J93HIqUt2Kkxp3gEOgC"
is_byok
false
latency
76
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"DeepInfra"
status
200
total_cost
0.0069758
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
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
66.12%
Dialogue to Total Word Ratio
Ratio: 98.02%, Deviation: 8.02%
neededClean
false
wordsTotal
202
wordsDialogue
198
83.0609%