NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZTY860NY1ZRKM2DJYKPSNT
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.9s
Cost:
$0.012890
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
66.3873%
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
"We're stealing from children, Bill. Actual small children." "Rich children, Molly. There's a difference." "Enlighten me." "Rich children have butlers. Butlers have pension plans. Ergo, victimless crime." "That's not how ergo works." "Look, the Pemberton kid's turning seven. You know what seven-year-olds get these days? iPads. Drones. One kid last year got a pony." "We're not stealing a pony, Bill." "I'm just saying, ponies have resale value." "How do you even fence a pony?" "Craigslist, Molly. Keep up." "Okay, fine. What's the plan?" "I dress as a clown. You dress as the entertainment." "What entertainment?" "Princess Sparklebottom." "Absolutely not." "She's booked. I canceled her. You've got the tiara in the bag." "Bill." "The children will be distracted by balloon animals while you gather the gifts into the 'magic treasure chest.'" "Which is?" "A duffel bag I spray-painted gold." "And the parents?" "Open bar. Trust me, by three o'clock those parents won't notice if we stole the house." "And if someone catches us?" "We cry. Loudly. Claim we're method actors going through a divorce." "That's your exit strategy?" "Molly, darling, I've escaped a bar mitzvah, a baptism, and a quinceaƱera. Trust the process."
created_at
"2026-04-24T13:30:18.701Z"
4/24/2026, 1:30:18 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
841
moderation_latency
(null)
generation_time
8844
tokens_prompt
77
tokens_completion
351
native_tokens_prompt
98
native_tokens_completion
496
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
0.01289
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"4febb210-7cdb-4884-873f-5b1510eec893"
is_byok
false
latency
841
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-1777037418-l10BhSUYoAB5Qpc3kHHf"
session_id
(null)
api_type
"completions"
id
"gen-1777037418-RaZxZIMRmwL5z1DHd6k1"
upstream_id
"4febb210-7cdb-4884-873f-5b1510eec893"
total_cost
0.01289
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
195
wordsDialogue
195
66.3873%