NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ937YAM3XCRGCY6FZF5MR9
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.1s
Cost:
$0.004770
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
97.70%
Dialogue to Total Word Ratio
(details)
86.4300%
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
"Okay, so the party starts at two," Molly whispered, unfolding a hand-drawn map onto the car hood. "Who draws a map to a Chuck E. Cheese?" Bill asked. "Professional thieves, Bill. Professional thieves." "We're stealing birthday presents from seven-year-olds." "Allegedly stealing. Stay positive." Bill squinted at the map. "Why is the bouncy castle labeled threat level orange?" "Have you ever tried running through one? You lose thirty seconds minimum. It's a death trap." "What's this circle marked the zone of no return?" "The face painting station. Last job I got turned into a butterfly and couldn't shake it for a week. Very hard to be intimidating as a butterfly." "You've done this before?" "Twice. Christmas and Easter. Very seasonal work." Bill rubbed his temples. "The moral implications are really hitting me right now." "The presents go to a thrift store, Bill. We talked about this." "Did we though?" "Mostly in my head, yes." "So what's the exit strategy?" "We blend in." "How?" "I got you a cape and a little wizard hat." Bill stared at her. "I'm a grown man." "You're a wizard, Bill."
created_at
"2026-02-18T02:26:12.740419+00:00"
2/18/2026, 2:26:12 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
756
moderation_latency
(null)
generation_time
9024
tokens_prompt
77
tokens_completion
311
native_tokens_prompt
75
native_tokens_completion
303
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
0.00477
router
(null)
provider_responses
0
id
"msg_01FQUGSExDKzSXJeCgccunme"
status
200
is_byok
false
latency
756
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381563-yVS6kpukmm9tIqN0GgjK"
upstream_id
"msg_01FQUGSExDKzSXJeCgccunme"
total_cost
0.00477
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
187
97.70%
Dialogue to Total Word Ratio
Ratio: 86.10%, Deviation: 3.90%
neededClean
false
wordsTotal
187
wordsDialogue
161
86.4300%