NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ93GSSK5HBGQT9T2DD8YH8
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.7s
Cost:
$0.005265
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
67.4963%
Overall
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
"Right, so here's the plan," Molly whispered, spreading a crayon drawing across the table. "Is that map drawn in crayon?" Bill asked. "I borrowed it from their recycling bin. Focus." "It smells like grape." "Bill!" "Sorry, sorry. Continue." "We go in through the bouncy castle." "The bouncy castle." "Keep your voice down. Yes, the bouncy castle. It connects to the garden where the presents are stacked." "And nobody will notice two adults bouncing through a children's party?" "We'll wear party hats." Bill stared at her. "That's your disguise? Party hats?" "And I have a balloon animal." "Oh well, a balloon animal changes everything." "Sarcasm is not helpful right now." "Neither is this plan! What if someone recognises us?" "We say we're the entertainment." "Can you even make balloon animals?" "I've been practicing." "What can you make?" "Snakes." "Just snakes?" "Very convincing snakes." "Right. And once we grab the presents, we run?" "We walk calmly to the catering van outside." "You hired a catering van?" "I borrowed it." "From whom?" Molly shifted her eyes sideways. "The actual caterers." "Molly." "In and out, Bill."
created_at
"2026-02-18T02:26:21.872631+00:00"
2/18/2026, 2:26:21 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
431
moderation_latency
(null)
generation_time
8640
tokens_prompt
77
tokens_completion
336
native_tokens_prompt
75
native_tokens_completion
336
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
0.005265
router
(null)
provider_responses
0
id
"msg_01WDtAf5RrZw9qShnmUBvUUc"
status
200
is_byok
false
latency
431
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381572-87muON5FQHbYS6nA6YR2"
upstream_id
"msg_01WDtAf5RrZw9qShnmUBvUUc"
total_cost
0.005265
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
35.00%
Matches word count
n/a
neededClean
false
words
182
99.99%
Dialogue to Total Word Ratio
Ratio: 89.01%, Deviation: 0.99%
neededClean
false
wordsTotal
182
wordsDialogue
162
67.4963%