NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM62KC3H952A8TPKR1QBXS1
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.1s
Cost:
$0.000247
Provider:
ModelRun
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
The storage closet of Molly and Bill’s hideout was cramped, lit by a single flickering bulb, and smelled faintly of expired cheese. Maps of suburban cul-de-sacs were taped haphazardly across the walls, each marked with red Sharpie. Molly adjusted her neon-green ski mask while Bill licked frosting off a stolen cupcake wrapper. "Focus, Bill," Molly sighed, slapping the wrapper out of his hand. "Relax," he mumbled, wiping crumbs on his pants. "Kids' parties are chaos—parents arguing over juice boxes, toddlers screaming, nobody’s watching the gift pile." Molly tapped a photo of Little Timmy Thompson’s backyard pinned to the wall. "Security detail: one golden retriever with a wagging tail, three sugared-up six-year-olds on a sugar crash, and Timmy’s dad, who’s probably nursing a beer in the garage." Bill grinned. "Perfect. We show up in clown costumes—blend right in." "Clowns aren’t subtle." "Neither is robbing a birthday party," he countered. Molly groaned but grabbed a red rubber nose from a bin. "Fine. But if we get tackled by a pack of kindergarteners, I’m blaming you." Bill tossed her a glittery balloon. "Deal." They high-fived, knocking over a stack of party hats. The heist was on.
created_at
"2026-02-16T21:35:41.28685+00:00"
2/16/2026, 9:35:41 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
736
moderation_latency
(null)
generation_time
7107
tokens_prompt
77
tokens_completion
328
native_tokens_prompt
66
native_tokens_completion
304
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
23
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00024728
router
(null)
provider_responses
0
id
"chatcmpl-196626fe757a494882cec900bb1c77f7"
status
200
is_byok
false
latency
89
endpoint_id
"a3938710-1b99-4a1f-85f4-2494f3f659d3"
provider_name
"ModelRun"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277733-NZcln3wPvDGX4WG0D2VL"
upstream_id
"chatcmpl-196626fe757a494882cec900bb1c77f7"
total_cost
0.00024728
cache_discount
(null)
upstream_inference_cost
0
provider_name
"ModelRun"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
0.0000%
Dialogue to Total Word Ratio
Ratio: 41.09%, Deviation: 31.09%
neededClean
false
wordsTotal
202
wordsDialogue
83
49.9920%