NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2GW80QFZNC05S55XWBYPE0
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10m 39s
Cost:
$0.090942
Provider:
Together
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 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 pointed at the crudely drawn map. "Alright, Bill, here's the target: the gift table. Guarded by toddlers but protected by their parents' ever-watchful eyes." Bill leaned close. "So what's the play? We blend in? I can put on a onesie." "Too conspicuous. We create a diversion. I'll be the magician. I'll make the cake disappear." "Then they'll just cut the second cake. Kids always have a backup cake." Molly sighed. "Fine, then the piñata. We rig it so when it breaks, we grab the presents in the confusion." Bill grimaced. "But what about the big kids? They're sneaky and fast." "Leave them to me. I'll bribe them with extra goody bags. Now, timing is crucial. At my signal—when I shout 'Happy Birthday!'—you move." "Got it. What's the getaway vehicle?" Molly beamed. "A tricycle disguised as a fire truck. No one will look twice." "And if we're cornered?" "We claim we're the entertainment and start juggling." "Juggling? You can't juggle." "I've been practicing with napkins." Bill groaned. "This'll be a disaster." Molly added, "Trust me, it's foolproof. Now let's go over the plan once more. Operation Gift Grab begins at noon." "What could possibly go wrong?" "With you? Everything."
created_at
"2026-04-25T14:32:21.352Z"
4/25/2026, 2:32:21 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
345
moderation_latency
(null)
generation_time
627647
tokens_prompt
77
tokens_completion
18954
native_tokens_prompt
146
native_tokens_completion
20599
native_tokens_completion_images
(null)
native_tokens_reasoning
18625
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
0.0909422
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
is_byok
false
latency
398
model_permaslug
"deepseek/deepseek-v4-pro-20260423"
provider_name
"DeepSeek"
status
429
1
endpoint_id
"13bda129-f8a6-4a60-b1db-98082e5f7ccd"
id
"ogZgAzC-2dTqGa-9f1e0e8007eb26d3"
is_byok
false
latency
345
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-1777127541-bDPaup9VrEeHqQLXcXuU"
session_id
(null)
api_type
"completions"
id
"gen-1777127541-LZHf4QkWba5dsdlNXP1J"
upstream_id
"ogZgAzC-2dTqGa-9f1e0e8007eb26d3"
total_cost
0.0909422
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
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: 90.05%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
181
100.0000%