NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KAY2FE5S96PZBFVGMJHBAD
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.2s
Cost:
$0.000134
Provider:
BaseTen
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
99.68%
Dialogue to Total Word Ratio
(details)
97.8330%
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
“Okay, run it by me again,” Molly said, adjusting her ski mask. “We’re robbing a birthday party?” “Not robbing. Liberating,” Bill whispered, peering through the hedge. “The presents are just sitting there. Unguarded. It’s a goldmine of Frozen-themed merchandise.” “We’re stealing from children, Bill.” “We’re stealing from parents who bought too much. That’s ethically different.” “How?” “Because the kids don’t pay for anything. They just cry when it’s gone. The parents cry when they see the credit card bill. We’re actually providing emotional release.” Molly sighed. “And the bouncy castle?” “Decoy. I’ll inflate it with the helium tank from the clown’s car.” “You’re going to steal the clown’s helium?” “I’m going to borrow it. Permanently.” “And the magician?” “I’ll distract him. I told him I’m a talent scout. He’s doing card tricks for me right now.” “You’re a terrible liar.” “I’m an excellent liar. He thinks I’m from Disney.” “Disney doesn’t scout at a backyard party in Jersey.” “He doesn’t know that. Look, Molly, do you want a Paw Patrol ride-on or not?” She paused. “...They have Paw Patrol?” “The big one. With the working lights.” “Fine. But if we get caught, I’m telling them you’re my therapist.” “Deal. Now grab the gift bags. I’ll handle the cake.”
created_at
"2026-09-03T09:52:22.526Z"
9/3/2026, 9:52:22 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
967
moderation_latency
(null)
generation_time
4093
tokens_prompt
75
tokens_completion
481
native_tokens_prompt
147
native_tokens_completion
442
native_tokens_completion_images
(null)
native_tokens_reasoning
92
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
0.00013403
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788429142-Kd74deAlFeqcvcKlva1m"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788429142-E2C76QXCnqYsqaUauE4z"
upstream_id
"chatcmpl-bf516bb5dd5546ff946b1123a025865c"
provider_responses
0
endpoint_id
"47a93b18-a9c6-485b-9a47-2afb6ca790dc"
id
"chatcmpl-bf516bb5dd5546ff946b1123a025865c"
is_byok
false
latency
967
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"BaseTen"
status
200
total_cost
0.00013403
cache_discount
(null)
upstream_inference_cost
0
provider_name
"BaseTen"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
99.68%
Dialogue to Total Word Ratio
Ratio: 92.38%, Deviation: 2.38%
neededClean
false
wordsTotal
210
wordsDialogue
194
97.8330%