NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ95509QFCE0A0J4VQ281MQ
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.7s
Cost:
$0.004890
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
86.13%
Dialogue to Total Word Ratio
(details)
73.2025%
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 the birthday girl turns six at noon," Molly whispered, unrolling a crayon drawing she'd stolen from the fridge of the house next door. "Is that a map?" Bill squinted. "Did you draw this yourself?" "It's what I had available, Bill." "You drew a unicorn in the corner." "That's the getaway car." "It's a unicorn, Molly." "It has wheels. Focus. The presents will be stacked near the bouncy castle, which goes up at eleven." "And we're hiding where exactly?" "Inside the bouncy castle." Bill stared at her. "We're hiding inside the bouncy castle." "Nobody questions what's inside a bouncy castle before they inflate it." "Grown adults, Molly. We are grown adults." "Grown adults who need money." "Fair point. What about the clown?" "Pedro? He's with us." "You hired a criminal clown?" "I hired Pedro. The criminal part is a bonus." "And the children?" "They'll be distracted by cake." "You seem very confident about that." "Bill, I have never met a child who chose anything over cake. Not once in my life." Bill rolled up the unicorn map and sighed. "I hate that you're right."
created_at
"2026-02-18T02:27:14.897703+00:00"
2/18/2026, 2:27:14 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
446
moderation_latency
(null)
generation_time
8629
tokens_prompt
77
tokens_completion
308
native_tokens_prompt
75
native_tokens_completion
311
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
0.00489
router
(null)
provider_responses
0
id
"msg_01GGwcJ8tTw8ZdgrKVvMYnRK"
status
200
is_byok
false
latency
446
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381625-IOZQfGBd7ldqHgVvN418"
upstream_id
"msg_01GGwcJ8tTw8ZdgrKVvMYnRK"
total_cost
0.00489
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
185
86.13%
Dialogue to Total Word Ratio
Ratio: 83.78%, Deviation: 6.22%
neededClean
false
wordsTotal
185
wordsDialogue
155
73.2025%