NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5PBAN7052T444K2CKFWQB
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.8s
Cost:
$0.000129
Provider:
AtlasCloud
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
“I can’t believe we’re casing a six-year-old’s birthday,” Bill muttered, peering through binoculars. “It’s genius,” Molly said, crouched beside him. “Low security. Predictable patterns. They’ll be focused on the cake.” “And the clown. Don’t forget the clown. I hate clowns.” “The clown is our signal. The second he starts making balloon animals, everyone will be in the backyard. We go in through the garage, hit the present table in the living room, and we’re out.” “What about the loot? It’s all toys.” “Have you seen toy prices? That’s high-value merchandise. We fence it online. ‘Never opened, slight glitter stain.’ We’ll make a fortune.” “I still think we should’ve brought a bigger bag.” “The giant gift bag *is* the bag, Bill. We walk in looking like guests who forgot to leave our present. We walk out with it full. It’s stealth.” “What’s our cover if someone stops us?” Molly handed him a party hat. “We’re the fun aunt and uncle. Now stop worrying. Remember the plan.” Bill put on the hat with a sigh. “The balloon dog. I see a balloon dog, we move.” “See? You’re a natural. Now smile. It’s a party.”
created_at
"2026-02-16T21:29:00.038593+00:00"
2/16/2026, 9:29:00 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1193
moderation_latency
(null)
generation_time
7752
tokens_prompt
77
tokens_completion
330
native_tokens_prompt
67
native_tokens_completion
294
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
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
0.00012914
router
(null)
provider_responses
0
id
"16b4a3c26b804004998cb003ed0a4a5d"
status
200
is_byok
false
latency
1193
endpoint_id
"3570a950-b80f-4acd-bb92-8e1c1c51fafc"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277331-N84TZqLtroj1sFuA1J5Y"
upstream_id
"16b4a3c26b804004998cb003ed0a4a5d"
total_cost
0.00012914
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
195
99.7168%
Dialogue to Total Word Ratio
Ratio: 87.69%, Deviation: 2.31%
neededClean
false
wordsTotal
195
wordsDialogue
171
99.5469%