NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5D1JJN5X9Y09BKSCCB2RW
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.1s
Cost:
$0.000405
Provider:
Novita
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 adjusted the fake mustache glued above her lip, squinting at the party invitation in her hand. The backyard of the Thompson residence was a riot of balloons, streamers, and sugar-hyped children. Bill, dressed as a clown with suspiciously smeared makeup, nudged her with an elbow. "This is the dumbest plan we’ve ever had," he muttered, juggling three rubber balls—badly. One smacked a toddler in the face. The kid blinked, then burst into tears. Molly sighed. "We blend in. We grab the loot. We leave. Easy." "Easy? I’m sweating glitter!" Bill hissed, wiping his brow and leaving a rainbow streak. A piñata swung overhead, bursting under the assault of a blindfolded seven-year-old. Candy rained down like loot from a vault. Molly’s eyes gleamed. "See? Distraction built in." Bill groaned as a parent thrust a plate of cake into his hands. "I’m allergic to joy." "Just stick to the plan." "Which part? The part where we stuff a bouncy castle full of presents and roll it away?" Molly grinned. "Exactly." Across the yard, a child pointed at Bill. "That clown smells like bad decisions." Molly patted his shoulder. "You’re nailing this."
created_at
"2026-02-16T21:23:59.763562+00:00"
2/16/2026, 9:23:59 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1463
moderation_latency
(null)
generation_time
12076
tokens_prompt
77
tokens_completion
313
native_tokens_prompt
66
native_tokens_completion
291
native_tokens_completion_images
0
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
0.0004047
router
(null)
provider_responses
0
id
"b43c6fcbefc59392df90c3cd846c51c5"
status
200
is_byok
false
latency
1462
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277026-blTuSJvv76bwCtbZRIi5"
upstream_id
"b43c6fcbefc59392df90c3cd846c51c5"
total_cost
0.0004047
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
98.7124%
Matches word count
n/a
neededClean
false
words
194
0.0000%
Dialogue to Total Word Ratio
Ratio: 31.96%, Deviation: 21.96%
neededClean
false
wordsTotal
194
wordsDialogue
62
49.3562%