NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ91RSWVDDYEHA2H93YH47J
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.3s
Cost:
$0.004800
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.3562%
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 crouched behind the hedge, binoculars pressed against her eyes, watching six-year-olds bounce on a inflatable castle. She scratched her chin thoughtfully. "The piñata is a decoy," she whispered. Bill looked up from his hand-drawn diagram. "What?" "The piñata. It's designed to distract us." "Molly, it's a donkey made of paper mache." "Exactly what they want you to think." She snatched the diagram from his hands and circled the area marked presents. "We go in through the bouncy castle, blend with the children, grab the goods." Bill stared at her. "We are both forty-three years old." "Hats," she said, producing two tiny birthday hats from her jacket. "Nobody questions a hat." Bill placed the elastic band under his chin and immediately felt his dignity leave his body entirely. A passing dog barked at him. "The real problem," Molly continued, completely unbothered, "is the clown. He sees everything." "Why are we doing this again?" "Because Gerald from accounting got a much better present than us at the office party and this is technically his nephew's birthday." Bill considered this for a long moment. "Fair enough," he said. "Give me a hat."
created_at
"2026-02-18T02:25:22.970556+00:00"
2/18/2026, 2:25:22 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
754
moderation_latency
213
generation_time
7037
tokens_prompt
77
tokens_completion
315
native_tokens_prompt
75
native_tokens_completion
305
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
0.0048
router
(null)
provider_responses
0
id
"221a24e2-298e-4b76-8dcb-4f214bcb1025"
status
200
is_byok
false
latency
753
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381515-Y5uljeKKJjcPseNO2mEr"
upstream_id
"221a24e2-298e-4b76-8dcb-4f214bcb1025"
total_cost
0.0048
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
194
wordsDialogue
97
99.3562%