NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ92C9YK2RAKW0JKREBBMP3
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.1s
Cost:
$0.005025
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
99.26%
Dialogue to Total Word Ratio
(details)
75.5932%
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 two o'clock," Molly whispered, unrolling a crayon-drawn map across the kitchen table. "Why do you have a map drawn in crayon?" Bill asked. "I drew it on site. I had to blend in." "You're forty-three." "Children trust me." "Children fear you, Molly." "Same thing. Now focus. The presents are stacked near the bouncy castle." "There's a bouncy castle?" "Don't get excited." "I'm not excited." "You're doing your excited face." "I don't have an excited face." "Bill, we're stealing from children. Compose yourself." "Right, yes. Sorry. How do we get past the clown?" "There's a clown?" "Big one. Suspicious eyes." "All clown eyes are suspicious." "These are particularly suspicious. He looked at me like he knew things." "He's a clown at a birthday party, Bill, he doesn't know things." "Famous last words." "We go in at cake time. Everyone looks at the cake." "And if someone spots us?" "We grab a balloon animal and act natural." "Act natural while holding a balloon animal." "Exactly." "This is the worst plan you've ever had." "Top five, maybe."
created_at
"2026-02-18T02:25:43.657857+00:00"
2/18/2026, 2:25:43 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
410
moderation_latency
(null)
generation_time
8084
tokens_prompt
77
tokens_completion
318
native_tokens_prompt
75
native_tokens_completion
320
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
0.005025
router
(null)
provider_responses
0
id
"msg_017Yfm5XrAo2cLZGxvZ3us39"
status
200
is_byok
false
latency
410
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381535-TwkxPfIXUrwdTLvirXdn"
upstream_id
"msg_017Yfm5XrAo2cLZGxvZ3us39"
total_cost
0.005025
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
184
99.26%
Dialogue to Total Word Ratio
Ratio: 92.93%, Deviation: 2.93%
neededClean
false
wordsTotal
184
wordsDialogue
171
75.5932%