NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DQXZPM85BVB8K4CX3Z2Z9
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
17.3s
Cost:
$0.005646
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
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: Okay, Bill, the target is Little Timmy's seventh birthday party. The presents are stacked by the bouncy castle. Bill: Bouncy castle? That's a tactical nightmare. Kids bounce unpredictably. Molly: We go in as clowns. Nobody suspects clowns. Bill: I'm not wearing the big shoes again. Last time I tripped over a piƱata and got beaten by a toddler with a plastic sword. Molly: Fine. You're the magician. I'm the balloon artist. We distract, then swipe the goods. Bill: What about the parents? Molly: They'll be drunk on juice boxes and small talk. Easy. Bill: And the dog? Molly: What dog? Bill: The birthday dog. He's wearing a party hat and he knows things. Molly: We bring bacon. Problem solved. Bill: What about the cake? Can we steal the cake too? Molly: No, Bill. We're professionals. Presents only. Bill: But it's got a dragon on it. Molly: Focus. We need Santa's sack, a getaway trike, and a fake allergy attack. Bill: I can do the allergy attack. I'm allergic to responsibility. Molly: Perfect. At three o'clock, when they sing, we strike. Bill: What if they sing Happy Birthday twice? Molly: Then we improvise, Bill. Grab the glitter glue and run.
created_at
"2026-09-10T10:27:46.812Z"
9/10/2026, 10:27:46 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
956
moderation_latency
(null)
generation_time
17244
tokens_prompt
75
tokens_completion
3717
native_tokens_prompt
93
native_tokens_completion
4682
native_tokens_completion_images
(null)
native_tokens_reasoning
4379
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
0.0056463
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789036066-0vZWfBmZspzo9cpQLbBI"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789036066-xQl99qiKuoOgXYdWVLLF"
upstream_id
"f68b5acf8d87e55656888e6649c1ffb3"
provider_responses
0
endpoint_id
"dac120e6-b2d2-44d4-8698-07844c6b84da"
id
"f68b5acf8d87e55656888e6649c1ffb3"
is_byok
false
latency
405
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"Novita"
status
200
total_cost
0.0056463
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
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
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
200
wordsDialogue
0
50.0000%