NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZV8WD0H1Y1409JVRTRQG8E
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.5s
Cost:
$0.012265
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
63.6358%
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
"Molly, I'm telling you, we hit the piñata first." "Bill, we are not hitting the piñata." "It's a distraction! Candy everywhere, kids scrambling, nobody's watching the gift table." "The gift table is literally our target. You want to bury it in Smarties?" "Fine. What's your plan, genius?" "We go in as entertainers. You're the clown, I'm the magician." "Why do I have to be the clown?" "Because you already have the shoes, Bill." "These are orthopedic!" "They're size seventeen and red." "...Okay, fair. So I clown around, you magic the presents into a bag?" "Exactly. Classic misdirection. 'Is this your card?' Poof, the Nintendo Switch is gone." "What about the parents?" "Sheet cake. Nobody suspects a man holding sheet cake." "That's beautiful. What if someone asks who hired us?" "Aunt Linda." "There's always an Aunt Linda." "Statistically, yes." "And the escape?" "Ice cream truck. Parked out back, engine running, jingle muted." "Molly, you thought of everything." "Almost. Bill, please, for the love of God, do not eat the cupcakes this time." "That was one heist—" "You went into a sugar coma in a bouncy castle." "I said I was sorry."
created_at
"2026-04-24T13:36:07.084Z"
4/24/2026, 1:36:07 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
791
moderation_latency
(null)
generation_time
7441
tokens_prompt
77
tokens_completion
331
native_tokens_prompt
98
native_tokens_completion
471
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
0.012265
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"5fd9fa4b-f82a-465e-8a02-b287814a575a"
is_byok
false
latency
791
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-1777037767-kUM37cidODHSnhWbLm0U"
session_id
(null)
api_type
"completions"
id
"gen-1777037767-XsHfZ6yWlTpnqav363aL"
upstream_id
"5fd9fa4b-f82a-465e-8a02-b287814a575a"
total_cost
0.012265
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
190
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
190
wordsDialogue
190
63.6358%