NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRK2923Q39G3YBCQN4TXE6
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
23.0s
Cost:
$0.031840
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 50% 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 blueprint across the hood of the van, smoothing it with the reverence of a surgeon laying out instruments. It was, technically, a placemat from a Pizza Hut, but she had drawn on it extensively. "Right," she said. "The Hendersons' back garden. Bouncy castle here, buffet table here, presents stacked on the trestle table under the gazebo. Twenty-two children, four adults, one clown." "One clown," Bill repeated. "One clown." "See, that's my problem. That's the whole problem, right there in three words." "Bill." "I don't like clowns, Molly. I've never liked clowns. My uncle Ray was a clown and he owed money to men who broke his accordion." Molly pinched the bridge of her nose. "The clown is an *opportunity*. The clown is doing balloon animals at two-fifteen. Every child in that garden will be watching him twist a poodle out of a long pink sausage. Nobody watches presents when there's a poodle situation developing." "And the adults?" "Prosecco. It's a children's party in a nice postcode. By two-fifteen those parents will have unhinged their jaws." Bill chewed his thumbnail and studied the placemat. "What's this bit? This scribbly bit by the shed?" "Dog." "What kind of dog?" "Small," Molly said, a fraction too quickly. "Molly." "It's a Yorkshire terrier called Baxter and he has one functioning eye and a personal vendetta against the postal service, which, last I checked, neither of us represents." "He'll bark." "Everything at that party will be barking. Twenty-two children hopped up on Fanta and a bouncy castle, Bill. Baxter's contribution will be lost in the general symphony." She tapped the placemat. "We come over the fence at two-twelve. You take the wheelbarrow—" "Why am I on wheelbarrow?" "Because I've seen you try to carry things and I've seen you try to push things, and pushing is where your talent lives." Bill absorbed this as a compliment, which had been the intention. "Fine. Wheelbarrow. Then what?" "You load, I cover. Thirty seconds, back over the fence, into the van, gone before the poodle's got a tail." "And if someone stops us?" "We're the entertainment. We're here for the piñata." "There's a piñata?" "There's always a piñata," Molly said, "in the mind of a suspicious adult who has had three glasses of prosecco and wants to believe two people in a garden with a wheelbarrow are professionals." Bill folded his arms. "And what exactly are we stealing? These are seven-year-olds. It's going to be plastic dinosaurs and vouchers." Molly turned to him slowly, and something holy came into her eyes. "The birthday girl is Amelia Henderson. Her grandfather is Terrence Henderson. Of Henderson Fine Jewellery. And Terrence, God bless his sentimental heart, has been telling the entire golf club that his granddaughter is getting the emerald pendant that his own mother wore in 1953." A long silence. Somewhere down the road, a child screamed with joy. "Wrapped," Bill said quietly. "Wrapped," Molly agreed, "and sitting on a trestle table under a gazebo, between a Lego set and a colouring book, guarded by a man in enormous shoes." Bill picked up the wheelbarrow. "Two-twelve."
created_at
"2026-07-25T13:49:15.434Z"
7/25/2026, 1:49:15 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3204
moderation_latency
(null)
generation_time
22862
tokens_prompt
75
tokens_completion
858
native_tokens_prompt
93
native_tokens_completion
1255
native_tokens_completion_images
(null)
native_tokens_reasoning
49
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
0.03184
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNt7aVW3r8SD7JwhQCsb"
is_byok
false
latency
1439
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-1784987355-HP7oaOsU2AjWMGcFeguc"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987355-ELfcKc2ujWBzdQcbd3xd"
upstream_id
"msg_011CdNt7aVW3r8SD7JwhQCsb"
total_cost
0.03184
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
519
0.00%
Dialogue to Total Word Ratio
Ratio: 77.80%, Deviation: 27.80%
neededClean
false
wordsTotal
527
wordsDialogue
410
13.5829%