NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM63B0NRJXW4JKXWSH8M281
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.0s
Cost:
$0.000128
Provider:
AtlasCloud
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 peered through the binoculars. “The target is heavily fortified. Sentries are armed with juice boxes.” Bill adjusted his black beanie. “Our intel says the main haul is in the living room, near the inflatable dragon. Extraction at piñata rupture, when chaos is maximal.” “The password is ‘unicorn sparkle,’” Molly said, deadpan, lowering the lenses. “You sure you can handle the toddler perimeter? They’re swift and unpredictable.” “My cover is foolproof.” Bill puffed out his chest. “I am ‘Uncle Bill,’ bearer of glow sticks and excessive candy. I will cause a sugar-fueled diversion.” Molly nodded, unfolding a crudely drawn map on the car hood. “I’ll go in through the sunroom. You keep the birthday boy’s father occupied. Talk about golf. Or carburetors.” “What’s the exit strategy?” “Same as infiltration, but faster. We load the swag into the oversized clown car we ‘borrowed.’ If compromised, we deploy the ultimate weapon.” Bill raised an eyebrow. “The glitter bomb?” “The glitter bomb,” Molly confirmed. “It’s a mercy they’ll never see coming. Now, synchronize your watches. Operation: Loot Bag commences in ten minutes. Remember, no honor among thieves… but we *do* leave the handmade cards.”
created_at
"2026-02-16T21:36:07.116007+00:00"
2/16/2026, 9:36:07 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1213
moderation_latency
(null)
generation_time
9007
tokens_prompt
77
tokens_completion
345
native_tokens_prompt
67
native_tokens_completion
291
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
0.000128
router
(null)
provider_responses
0
id
"93c0a1f7b36b431eae0781ed15477e0c"
status
200
is_byok
false
latency
1213
endpoint_id
"3570a950-b80f-4acd-bb92-8e1c1c51fafc"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277757-c02JL87fydYJk8k2ES8L"
upstream_id
"93c0a1f7b36b431eae0781ed15477e0c"
total_cost
0.000128
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
192
0.0000%
Dialogue to Total Word Ratio
Ratio: 80.21%, Deviation: 30.21%
neededClean
false
wordsTotal
192
wordsDialogue
154
47.9934%