NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5MJQSW8FYQPQZ23D6WTRW
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.0s
Cost:
$0.000865
Provider:
WandB
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 fence, squinting at the bouncy castle. “You’re sure the kid’s loaded?” Bill adjusted his fake mustache, grinning. “Trust me. Five-year-old with a trust fund? That piñata’s stuffed with IOUs from daddy’s hedge fund.” “So we just… waltz in?” “Nah, we’re the entertainment. Clown and magician duo.” Bill pulled a rubber chicken from his jacket. “You’re the clown.” “No way. I hate clowns.” “Perfect! You’ll blend right in.” Molly groaned. “Fine. But how do we haul out the loot?” Bill tapped his nose. “Toy sacks. Dump the presents, fill ’em with balloons—total distraction.” “And the parents?” “Piñata protocol. Whack it too hard, candy rains down, chaos ensues.” Molly shook her head. “This is the dumbest plan we’ve ever had.” “Correction—it’s the dumbest plan that’ll make us rich.” He tossed her a red nose. “Now honk for freedom.” She sighed, squeezing the nose. It let out a pathetic squeak. Bill clapped. “Perfect. Let’s go rob some toddlers.”
created_at
"2026-02-16T21:27:58.325926+00:00"
2/16/2026, 9:27:58 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
157
moderation_latency
(null)
generation_time
3940
tokens_prompt
77
tokens_completion
307
native_tokens_prompt
69
native_tokens_completion
286
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
0.00086516
router
(null)
provider_responses
0
id
"chatcmpl-6057a75be0d9456b803fe32170fe81a1"
status
200
is_byok
false
latency
57
endpoint_id
"78b3f653-4585-4c35-9a42-e3da2d6597ad"
provider_name
"WandB"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277273-7wRRH2dVzyFYg3fB3QIX"
upstream_id
"chatcmpl-6057a75be0d9456b803fe32170fe81a1"
total_cost
0.00086516
cache_discount
(null)
upstream_inference_cost
0
provider_name
"WandB"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
162
0.0000%
Dialogue to Total Word Ratio
Ratio: 67.28%, Deviation: 22.72%
neededClean
false
wordsTotal
162
wordsDialogue
109
0.0000%