NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DRFK5NAQ8XW114CMC7BW0
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
27.7s
Cost:
$0.004163
Provider:
DeepSeek
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 50% 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 spread a glitter-smeared map across the stolen picnic table while Bill nervously braided a party streamer. "The party starts at noon, and parents will be exhausted by cake." "That's when we strike." Bill frowned at the clown schedule. "Let's target the bouncy castle. Presents toss easier over the fence." "And attract sugar-crazed kids? No. We dress as caterers, wheel in a fake cake, and load gifts inside." "The cake?" "The cake's hollow, Bill." He brightened. "I love hollow cake." Molly pointed at the guest list. "We enter during pin the tail, grab the loot, and exit before the magician pulls a rabbit from somewhere illegal." "What if a kid sees?" "We offer frosting." "Frosting?" "Frosting and a mild threat about Santa's surveillance." Bill nodded. "Solid. Except the part where you said mild." The plan required timing, nerve, and a stroller large enough for forty wrapped boxes. Bill practiced his innocent face. Outside, a toddler screamed at a balloon. Molly ignored it and circled the gift table in red crayon. Bill checked his fake mustache in a spoon. A clown honked nearby. Bill flinched. Molly taped the map to the table and smiled like a tax auditor. They rehearsed quietly.
created_at
"2026-09-10T10:28:04.843Z"
9/10/2026, 10:28:04 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
870
moderation_latency
(null)
generation_time
27675
tokens_prompt
75
tokens_completion
6369
native_tokens_prompt
93
native_tokens_completion
6915
native_tokens_completion_images
(null)
native_tokens_reasoning
6635
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
0.00416295
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789036084-xoFlkuj5x8E0JHjTai16"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789036084-UsvzhJ9ZZXWDaNmKoxhZ"
upstream_id
"6312bef6-d810-4668-a62d-bfc6cd649eae"
provider_responses
0
endpoint_id
"fd104bc8-535a-4d31-a847-a8e402e86a02"
id
"6312bef6-d810-4668-a62d-bfc6cd649eae"
is_byok
false
latency
331
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"DeepSeek"
status
200
total_cost
0.00416295
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
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
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
202
wordsDialogue
101
100.0000%