NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DH698P4ZMGD54NVVXFGT6
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
17.7s
Cost:
$0.002472
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9595%
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 the stolen party invitation across a picnic table while Bill polished his clown nose. The candlelit spreadsheet listed gate codes, nap schedules, and which parent guarded the gift pile. Outside, a bouncy castle wheezed like a dying dragon. Somewhere, a children's party pulsed with sugar and chaos. Bill tapped a crayon map of the community center. Molly highlighted the snack table, the emergency exit, and the piñata's suspiciously reinforced rope. "So we pose as balloon artists, slip past the hired magician, and swipe every present before cake." "And the kids?" "Bribe them with frosting. They're tiny, corruptible, and have no legal standing." "Last time a toddler bit my shin and called me a bad Santa." "Then wear shin guards. I'll handle the gift table. You release the piñata." "That's candy, not cash." "Exactly. Candy causes riots. Riots cause cover." "What about the parents?" "Tell them we're doing a surprise charity raffle." "And the goat?" "The goat knows the back fence. Bring carrots." "Fine. But if a princess defeats us, I'm retiring." Bill nodded solemnly. Molly zipped her tool kit, checked her fake mustache, and practiced a cheerful clown honk. The plan was stupid, illegal, and only mildly likely to succeed. Perfect.
created_at
"2026-09-10T10:24:05.933Z"
9/10/2026, 10:24:05 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
984
moderation_latency
(null)
generation_time
17649
tokens_prompt
75
tokens_completion
3892
native_tokens_prompt
93
native_tokens_completion
4097
native_tokens_completion_images
(null)
native_tokens_reasoning
3811
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
0.00247215
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789035845-9q6RmbVSakpBTgHTK4F3"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789035845-1Ea1BVzgtZg5XkCnrqIN"
upstream_id
"f199ec47-e150-45dd-83bf-60d4b9a24b03"
provider_responses
0
endpoint_id
"fd104bc8-535a-4d31-a847-a8e402e86a02"
id
"f199ec47-e150-45dd-83bf-60d4b9a24b03"
is_byok
false
latency
420
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"DeepSeek"
status
200
total_cost
0.00247215
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
99.92%
Matches word count
n/a
neededClean
false
words
203
100.00%
Dialogue to Total Word Ratio
Ratio: 49.75%, Deviation: 0.25%
neededClean
false
wordsTotal
203
wordsDialogue
101
99.9595%