NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-16-01KHM5SZW9BNJVYW4Q322KH104
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6.8s
Cost:
$0.000216
Provider:
ModelRun
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
20.59%
Dialogue to Total Word Ratio
(details)
10.2952%
Overall
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
The warehouse loft stank of burnt coffee and old newspapers. Molly tossed a glittery invitation onto the rickety table. “Kid’s sixth birthday. Big house. Lousy security.” Bill squinted at the photo of a grinning boy clutching a dinosaur piñata. “We robbing manfaat now?” “Think bigger,” Molly said. “Parents loading presents into cars after the party. We swipe ’em before they do.” “From kids?” “They’re insured. Probably.” She unfolded a blueprint. “Two exits. Guard’s a golden retriever named Cupcake.” Bill groaned. “Last time dogs were involved, I lost a shoe.” “This one’s more interested in cake. Here’s the play: you’re the clown. Distract the kiddos while I load the loot.” Bill held up a neon-orாரু wig. “I look like a traffic cone.” “Perfect. No one suspects the guy who looks like a safety hazard.” She grinned. “Ten minutes tops.” Bill sighed. “If this goes south, I’m blaming the wig.” Molly patted his shoulder. “That’s the spirit.” Outside, a car alarm wailed like a bad omen.
created_at
"2026-02-16T21:30:58.887752+00:00"
2/16/2026, 9:30:58 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1477
moderation_latency
(null)
generation_time
6754
tokens_prompt
77
tokens_completion
301
native_tokens_prompt
66
native_tokens_completion
264
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
65
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
0.00021648
router
(null)
provider_responses
0
id
"chatcmpl-fa4b9bc305d748c89cfce8f3a6a61e98"
status
200
is_byok
false
latency
87
endpoint_id
"a3938710-1b99-4a1f-85f4-2494f3f659d3"
provider_name
"ModelRun"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277451-Pypr0pXFqX9QR9c3ECr5"
upstream_id
"chatcmpl-fa4b9bc305d748c89cfce8f3a6a61e98"
total_cost
0.00021648
cache_discount
(null)
upstream_inference_cost
0
provider_name
"ModelRun"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
164
20.59%
Dialogue to Total Word Ratio
Ratio: 61.21%, Deviation: 11.21%
neededClean
false
wordsTotal
165
wordsDialogue
101
10.2952%