NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZTV761TKWAXM9D50XWW04D
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.5s
Cost:
$0.011640
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
59.22%
Dialogue to Total Word Ratio
(details)
79.5716%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 blueprints across the card table, weighing the corners with half-empty cans of grape soda. The floor plan of the Peterson residence looked deceptively innocent, all sunrooms and mudrooms and a suspicious number of bathrooms for one family. Bill leaned over her shoulder, chewing a licorice rope with the grim focus of a man defusing a bomb. The party was Saturday. Tommy Peterson was turning seven, and according to the invitation Molly had steamed open at the mailbox, the theme was pirates. This detail delighted her enormously and troubled Bill deeply. Pirates meant eyepatches, and eyepatches meant depth perception problems, and depth perception problems meant he might trip over a toddler. "I hate toddlers," Bill muttered. Molly ignored him. She circled the back patio with a red marker, then drew an arrow toward the gift table, which she had labeled TREASURE in block letters. Thirty-two children had RSVP'd. Thirty-two children meant thirty-two gifts, minimum, and wealthy suburbanites always overspent out of competitive guilt. She tapped the marker against her teeth, calculating. A bounce house provided cover. A clown provided distraction. A piƱata provided chaos. Everything a working criminal could ask for, really, and cake besides.
created_at
"2026-04-24T13:28:39.375Z"
4/24/2026, 1:28:39 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
634
moderation_latency
(null)
generation_time
7449
tokens_prompt
77
tokens_completion
325
native_tokens_prompt
98
native_tokens_completion
446
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
usage
0.01164
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"e8595349-b992-43d9-8875-24b0c3859dc6"
is_byok
false
latency
634
model_permaslug
"anthropic/claude-4.7-opus-20260416"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777037319-v4AkFmp3QZ2GiI36JYXe"
session_id
(null)
api_type
"completions"
id
"gen-1777037319-1RxCObycah1megNOwRUO"
upstream_id
"e8595349-b992-43d9-8875-24b0c3859dc6"
total_cost
0.01164
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
59.22%
Dialogue to Total Word Ratio
Ratio: 1.49%, Deviation: 8.51%
neededClean
false
wordsTotal
201
wordsDialogue
3
79.5716%