NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZTWHJG2GEFVF5GBK376MGB
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.5s
Cost:
$0.012390
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
79.14%
Dialogue to Total Word Ratio
(details)
88.9285%
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 unfurled the blueprints across the sticky diner table, smoothing them flat with a ketchup bottle and a half-eaten pickle. The layout of the Peterson residence sprawled before them in blue ink, dotted with her frantic red annotations: bouncy castle, clown zone, piñata blast radius. Bill squinted, chewing thoughtfully on a toothpick he'd been nursing since Tuesday. The birthday was Saturday. Jimmy Peterson was turning seven, and according to Molly's intelligence—gathered by loitering suspiciously near a Toys "R" Us—the gift pile would be worth a conservative four hundred dollars in unopened plastic. "Clowns terrify me," Bill muttered. Molly rolled her eyes and tapped the diagram. The plan was elegant in its stupidity. Bill would enter disguised as Uncle Rodney, a relative so distant nobody would question his cargo shorts. Molly would infiltrate via the backyard, crawling beneath the hedge like a woodland predator, and begin systematically loading wrapped presents into a hollowed-out piñata they'd prepared that morning. Extraction would occur during the candle-blowing ceremony, when parental attention peaked and security collapsed. She'd rehearsed the timing using her nephew's baptism as a dry run. "Any questions?" Bill studied the clowns. He had several.
created_at
"2026-04-24T13:29:22.784Z"
4/24/2026, 1:29:22 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
674
moderation_latency
(null)
generation_time
7438
tokens_prompt
77
tokens_completion
333
native_tokens_prompt
98
native_tokens_completion
476
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
0.01239
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"7f919ec4-610d-4651-ab3d-9578e862446f"
is_byok
false
latency
673
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-1777037362-ncY0NTlcRpmcXLwk7fkl"
session_id
(null)
api_type
"completions"
id
"gen-1777037362-63UtzVlRq4n5LD3XcCzW"
upstream_id
"7f919ec4-610d-4651-ab3d-9578e862446f"
total_cost
0.01239
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
79.14%
Dialogue to Total Word Ratio
Ratio: 3.05%, Deviation: 6.95%
neededClean
false
wordsTotal
197
wordsDialogue
6
88.9285%