NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRAREXEB9PCFH6RWETMN4D
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
20.2s
Cost:
$0.029315
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
13.5829%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 table, smoothing them with the reverence of a surgeon. "Is that a napkin?" Bill asked. "It's a diagram." "It's a napkin with a bouncy castle drawn on it." "It's a *scaled* diagram," Molly said. "Now focus. Fourteen hundred hours, the Pemberton residence. Birthday girl is Sophie, turning seven, which means the presents will be piled in the conservatory, unguarded, while every adult in that house is watching a man named Bongo pull scarves out of his sleeve." "How do you know his name is Bongo?" "Because I'm Bongo." Bill set down his tea. "You're the magician." "I answered the ad. Two hundred quid, sandwiches included." "Molly, you can't do magic." "I can do the one where the coin disappears." "That's not magic, that's you keeping the coin." "It's *thematically* magic," Molly said. "Point is, I'm inside. I've got forty minutes of legitimate access to that conservatory while the parents film me on their phones. Which brings me to you." "I'm not being Bongo's assistant." "You're the clown." "Absolutely not." "Bill—" "I have a *reputation*." "You have a criminal record and a bad hip." Bill folded his arms. "What's the clown do?" "The clown does balloon animals in the hallway. Which means the clown is standing between the conservatory and every parent in that house, and when a mother wanders towards the presents, the clown says—" "Say it." "—the clown says, 'Would the lady like a giraffe?'" Bill closed his eyes. "How many giraffes are we talking." "Realistically? Thirty." "I can do a dog. I can't do a giraffe." "Then say it's a giraffe. They're four. They can't tell." "The *mothers* can tell, Molly, that's the entire problem with mothers—" "Then make dogs and tell them it's a dachshund exhibition, I don't care, this is not the crux of the operation." Molly tapped the napkin. "The crux is the wheelie bin." Bill leaned in. "Go on." "Green bin, side gate, collected Thursdays. We arrive Wednesday night, we line it with bin bags, and at fourteen-forty, while the children are singing, I load every present into the bin and roll it out the side gate to the van." "You're going to steal a seven-year-old's presents in a bin." "I'm going to steal *forty* seven-year-olds' presents in a bin. Do you know what these people buy? Sophie's father is a dentist. There will be iPads, Bill. There will be a scooter that costs more than my car." "Your car costs eighty pounds." "There will be *several* scooters." Bill was quiet a moment. "And the sandwiches?" "Included." "Egg?" "I'll ask." "Because if it's egg, I'm the clown." Molly extended her hand across the napkin. "Bill, in six hours you'll be a wealthy man in face paint." "In six hours I'll be arrested in a hallway holding a giraffe." "A dachshund." "A dachshund," Bill agreed, and shook her hand.
created_at
"2026-07-25T13:44:43.238Z"
7/25/2026, 1:44:43 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3071
moderation_latency
(null)
generation_time
20058
tokens_prompt
75
tokens_completion
791
native_tokens_prompt
93
native_tokens_completion
1154
native_tokens_completion_images
(null)
native_tokens_reasoning
53
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"
service_tier
"default"
usage
0.029315
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsmWCjHrbnYgkEpUZY7"
is_byok
false
latency
1265
model_permaslug
"anthropic/claude-opus-5-20260723"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784987083-65pTo4JGl6lBV09x3Nqf"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987083-ryJsQsBXLEBG34S3FWHF"
upstream_id
"msg_011CdNsmWCjHrbnYgkEpUZY7"
total_cost
0.029315
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
27.17%
Matches word count
n/a
neededClean
false
words
481
0.00%
Dialogue to Total Word Ratio
Ratio: 87.04%, Deviation: 17.04%
neededClean
false
wordsTotal
486
wordsDialogue
423
13.5829%