NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZV3GTSBXSTVTZH301M2M0K
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.7s
Cost:
$0.012940
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.0824%
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
"Bill, we are not stealing from a six-year-old." "Molly, we absolutely are. His dad's a hedge fund guy. Those presents are basically laundered money wrapped in SpongeBob paper." "It's a birthday party." "It's a *target-rich environment*." "There'll be clowns, Bill." "I'm not afraid of clowns." "You cried at the circus." "That was one time, and that mime was aggressive." "Okay, fine. How do we get in?" "Easy. I rented a bounce house. We show up as delivery guys, inflate the thing, grab the loot, deflate, roll out." "You rented a bounce house." "Under a fake name. 'Hoppy McJumperson.'" "Bill." "What?" "That is the stupidest alias I have ever heard, and I once worked with a man named Derek Derekson." "It's whimsical. Birthday parties love whimsy." "What about the parents?" "Goodie bags. Laced." "Bill!" "Laced with *cookies*, Molly, God, what kind of monster do you think I am?" "The kind robbing a first-grader." "A *wealthy* first-grader. Say it with the adjective, it sounds better." "And the presents?" "Into the bounce house. We deflate it with the loot inside. Nobody checks a sad pile of vinyl." "...Bill, that's actually brilliant." "I know. Now grab the clown nose."
created_at
"2026-04-24T13:33:11.397Z"
4/24/2026, 1:33:11 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
635
moderation_latency
(null)
generation_time
7614
tokens_prompt
77
tokens_completion
340
native_tokens_prompt
98
native_tokens_completion
498
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
0.01294
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"f4d7bea9-d234-4ebe-b4b7-16be10afe39b"
is_byok
false
latency
635
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-1777037591-X6AfLL8sOHU1SzSZhpva"
session_id
(null)
api_type
"completions"
id
"gen-1777037591-tKZoCKfWBV3DHO5me42c"
upstream_id
"f4d7bea9-d234-4ebe-b4b7-16be10afe39b"
total_cost
0.01294
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
199
wordsDialogue
199
68.0824%