NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-20-01M5C6MHF30JNJA9K7AEPGD2EY
Run Details
Model:
DeepSeek V4.1 Flash 1017 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
13.0s
Cost:
$0.001030
Provider:
InferenceNet
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.0824%
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
"Bill, the clown suit is non-negotiable." "You said that about the goose, Molly, and we're still banned from three petting zoos." "This time the goose is a distraction. The birthday boy cries at clowns, the parents panic, we sweep the present table." "Sweep? We're not Santa's cleanup crew. We're professionals." "Professionals don't get arrested by a six-year-old with a juice box." "That was one time. She had surprisingly strong wrists." "Focus. Party starts at two. We enter as balloon artists, incapacitate the bouncy castle with a slow leak, and exit through the gift bag pile." "Define incapacitate." "Untie one knot. Chaos. Beautiful, low-speed chaos." "And the presents?" "By the cake table. We swap them for empty boxes labeled educational." "Monsters." "Educational monsters. Very hard to gift-wrap." "What about the magician?" "He's our inside man. He'll misdirect during Pin the Tail." "Does he know he's our inside man?" "Not yet. That's what makes it authentic." "Authentic? We're stealing from toddlers." "Toddlers are ruthless. Have you seen their negotiations?" "Fine. But I'm not wearing the clown nose." "It's a clown suit, Bill. The nose is attached." "Then I'm driving." "Deal. Grab the balloons and the fake beard." "Why the fake beard?" "For the getaway tricycle." "Of course."
created_at
"2026-10-20T08:25:22.155Z"
10/20/2026, 8:25:22 AM
model
"deepseek/deepseek-v4.1-flash-20261017"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
158
moderation_latency
(null)
generation_time
13017
tokens_prompt
75
tokens_completion
1898
native_tokens_prompt
67
native_tokens_completion
2049
native_tokens_completion_images
(null)
native_tokens_reasoning
1734
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
0.00102986
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1792484722-CpqM6v95DrdmsXSqLT94"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1792484722-4wwGRPrAMu1wuFeHVEYB"
upstream_id
"gv2_G3nW1wJrGkm9emtvVXteK"
provider_responses
0
endpoint_id
"4231aea9-73af-4a2f-bd14-660b1d8b13b2"
id
"gv2_G3nW1wJrGkm9emtvVXteK"
is_byok
false
latency
158
model_permaslug
"deepseek/deepseek-v4.1-flash-20261017"
provider_name
"InferenceNet"
status
200
total_cost
0.00102986
cache_discount
(null)
upstream_inference_cost
0
provider_name
"InferenceNet"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
210
wordsDialogue
210
68.0824%