NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8WDD7PQG7EZQQ1SNZA03CF
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.4s
Cost:
$0.006621
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
99.61%
Dialogue to Total Word Ratio
(details)
63.3880%
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 we go in through the back," said Bill, spreading the hand-drawn map across the table. "That's the bouncy castle, Bill." "The side, then." "That's where the clown is stationed." "There's a clown?" "There's always a clown, Bill." "Fine. The front door." "Brilliant. We'll just walk through forty seven-year-olds and their parents carrying empty sacks." "We bring gift bags. We blend in." "You're fifty three years old." "I have a young face." "You look like a haunted potato." "Molly, focus. We get in, we grab the presents, we're out before they cut the cake." "What kind of presents are we even talking about? Lego? Slime kits?" "The birthday kid is little Freddie Harrington. His dad's a hedge fund manager." "Oh." "The guest list alone has three Hugos and a Tarquin." "So we're talking Nintendo Switches. Remote control Ferraris." "And probably a pony voucher." "There's no such thing as a pony voucher." "Not yet there isn't." Molly stared at him for a long moment. "I want sixty percent." "Fifty five." "The clown, Bill. Sixty." Bill folded the map slowly. "Fine. Sixty."
created_at
"2026-02-24T22:30:44.74Z"
2/24/2026, 10:30:44 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1303
moderation_latency
(null)
generation_time
11244
tokens_prompt
77
tokens_completion
391
native_tokens_prompt
92
native_tokens_completion
423
native_tokens_completion_images
(null)
native_tokens_reasoning
75
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
0.006621
router
(null)
provider_responses
0
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
id
"msg_01X5GZ8kbdtEioDn9Ko3Swm2"
is_byok
false
latency
1270
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Anthropic"
status
200
api_type
"completions"
id
"gen-1771972244-w8dhECDTnLuxAwqmEp3Z"
upstream_id
"msg_01X5GZ8kbdtEioDn9Ko3Swm2"
total_cost
0.006621
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
27.17%
Matches word count
n/a
neededClean
false
words
181
99.61%
Dialogue to Total Word Ratio
Ratio: 87.50%, Deviation: 2.50%
neededClean
false
wordsTotal
184
wordsDialogue
161
63.3880%