NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5J1ZJDKAT0NPZKJ92NVRW
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
13.5s
Cost:
$0.000315
Provider:
DeepInfra
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
Molly peered over the hedge, clutching binoculars. "Bill, this is it. The jackpot of all jackpots." Bill adjusted his ski mask. "A kids’ party? Seriously? What are we stealing? Juice boxes?" Molly rolled her eyes. "No, genius. The presents. They’re piled up like Fort Knox in there. Think about it—tiny bikes, video games, action figures. It’s a treasure trove." Bill scratched his head. "You want us to rob a bunch of five-year-olds? Isn’t that, like, morally bankrupt?" Molly smirked. "Morals don’t pay the bills, Bill. Besides, they’ll get new ones. Ever heard of insurance?" Bill hesitated. "What if the parents catch us?" Molly waved dismissively. "Please. They’ll be too busy negotiating who gets the last piece of cake. We’ll be in and out before you can say ‘pin the tail on the donkey.’" Bill sighed. "Fine. But I’m not wearing the clown costume again." Molly grinned. "Too bad. It’s perfect camouflage. Now, here’s the plan: I’ll distract the kids with my world-famous balloon animals while you load the loot into the van." Bill groaned. "Balloon animals? Really?" Molly shrugged. "Hey, if it works, it works. Ready?" Bill muttered, "As I’ll ever be." Molly slapped his shoulder. "That’s the spirit. Let’s go ruin some childhoods."
created_at
"2026-02-16T21:26:45.050109+00:00"
2/16/2026, 9:26:45 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
259
moderation_latency
(null)
generation_time
13470
tokens_prompt
77
tokens_completion
345
native_tokens_prompt
66
native_tokens_completion
330
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
0.00031482
router
(null)
provider_responses
0
id
"chatcmpl-RCh6bD2CpuWBLnOmu4IkF6yW"
status
200
is_byok
false
latency
103
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277191-HWDbhVnuoa0eEwd2PgbV"
upstream_id
"chatcmpl-RCh6bD2CpuWBLnOmu4IkF6yW"
total_cost
0.00031482
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
208
41.0856%
Dialogue to Total Word Ratio
Ratio: 80.29%, Deviation: 9.71%
neededClean
false
wordsTotal
208
wordsDialogue
167
68.5362%