NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5MMB31VBCYWXDD6PCQGFH
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.7s
Cost:
$0.000420
Provider:
Novita
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 adjusted her oversized sunglasses and peered over the hedge. "You’re telling me this is the big score? A six-year-old’s birthday party?" Bill grinned, patting the empty sack slung over his shoulder. "Think about it—no security, no alarms, just a piñata and a bunch of sugar-crazed kids. Easiest job we’ve ever pulled." Molly sighed. "And what’s our exit strategy? Outrun a pack of toddlers on a juice-box high?" "Relax," Bill said, pulling a handful of candy from his pocket. "Distraction plan: I toss these into the bushes, kids swarm, we grab the loot. Boom." A tiny voice piped up behind them. "Are you guys magicians?" They turned to see a small boy in a dinosaur costume staring at them. Molly forced a smile. "Uh, yes! We’re here to… make the presents disappear!" The boy gasped. "Cool! Can I help?" Bill groaned. "Kid, this is a very delicate operation—" Molly elbowed him. "Absolutely! You’ll be our lookout. Just yell if you see any grown-ups coming." As the boy scampered off, Bill muttered, "We’re recruiting now?" "Adapt or perish," Molly said, adjusting her fake mustache. "Now, let’s go steal some Legos."
created_at
"2026-02-16T21:28:07.996194+00:00"
2/16/2026, 9:28:07 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1523
moderation_latency
(null)
generation_time
11654
tokens_prompt
77
tokens_completion
313
native_tokens_prompt
66
native_tokens_completion
303
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
0.0004203
router
(null)
provider_responses
0
id
"991e4921413feda6553afdab13cc3953"
status
200
is_byok
false
latency
1523
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277275-tUAc4eN1W1V6uL2gw24v"
upstream_id
"991e4921413feda6553afdab13cc3953"
total_cost
0.0004203
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
195
36.7879%
Dialogue to Total Word Ratio
Ratio: 60.00%, Deviation: 10.00%
neededClean
false
wordsTotal
195
wordsDialogue
117
68.0824%