NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ91R6V6KPK4NYXJZJNVJT1
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.0s
Cost:
$0.004860
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
97.9930%
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
Molly spread the crayon-drawn map across the hood of the van and stabbed her finger at a pink rectangle labeled "prezints." "The birthday girl turns six at two o'clock. That gives us exactly forty minutes before they cut the cake." Bill squinted at the map. "Who drew this, a child?" "I drew it, Bill." "Right, so a child." He scratched his chin. "What about the clown?" Molly pulled out a thick folder and flipped it open with professional gravity. The clown's headshot stared back at them. "Giggles McGee. Retired. Bad knees. He won't chase us past the bouncy castle." "And the parents?" "Occupied. Pin the tail on the donkey runs long when adults get competitive." Bill nodded slowly, absorbing the intelligence. A balloon drifted past the windshield on the breeze, and he watched it go with something almost resembling conscience. "These are kids' presents, Molly." "Wrapped, tagged, and totally resellable." "I want it noted I had reservations." "Noted." She handed him a party hat. "Now put this on. We need cover." Bill stretched the elastic under his chin and stared at himself in the mirror. "I look ridiculous." "You look invited."
created_at
"2026-02-18T02:25:23.767373+00:00"
2/18/2026, 2:25:23 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
853
moderation_latency
(null)
generation_time
8909
tokens_prompt
77
tokens_completion
310
native_tokens_prompt
75
native_tokens_completion
309
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
0.00486
router
(null)
provider_responses
0
id
"msg_01HKehP9osPosxa4jATj7fg1"
status
200
is_byok
false
latency
853
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381514-cZh9BZ7J0Hs270rDmU68"
upstream_id
"msg_01HKehP9osPosxa4jATj7fg1"
total_cost
0.00486
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
100.00%
Dialogue to Total Word Ratio
Ratio: 50.52%, Deviation: 0.52%
neededClean
false
wordsTotal
192
wordsDialogue
97
97.9930%