NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRC98VXEKCMP4CFTR7SABY
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
21.6s
Cost:
$0.030440
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
48.8143%
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
The blueprints were drawn on the back of a pizza box, which Bill considered his finest work. "Here's the bouncy castle," he said, tapping a lopsided rectangle with a pen. "Here's the trestle table with the sausage rolls. And here — " he drew a circle with such force the pen tore through cardboard — "is the present pile." Molly leaned over the box, chewing a thumbnail. "Bill, that's a shed." "It's a garden." "It's clearly a shed. You've drawn a little window on it." "That's the paddling pool, seen from above." "Then why does it have curtains?" Bill set down the pen with the wounded dignity of a man whose art has been misunderstood. "The point," he said, "is the timeline. Party starts at two. Cake at three. Twenty-two children, all of them sugared out of their minds, all of them screaming. Nobody hears a thing. We go in at three-oh-five and we're out by ten past with every gift-wrapped item in that garden." "And the mothers?" "Distracted." "By what?" "By the twenty-two screaming children, Molly. Keep up." Molly straightened and folded her arms. She had been doing this eleven years and had never once robbed anyone under four feet tall, a record she had privately been proud of. "I want to raise a concern," she said. "Raise it." "It's a seven-year-old's birthday party." "Correct." "We're stealing a seven-year-old's birthday presents." "Also correct. Is that the concern? Because that's just a summary." "The concern," Molly said, "is that I'll go to hell." Bill waved this off. "Nobody goes to hell for cardboard. Do you know what's in those parcels? Plastic. Plastic in boxes, wrapped in paper printed with more plastic. We're doing the landfill a favour. We're basically environmentalists." "Environmentalists who resell on the internet." "Circular economy," said Bill. Molly picked up the pizza box and studied it again, tilting it as though a different angle might make it competent. "What's this bit? This scribble by the fence?" "Dog." "There's a dog?" "There's a Labrador called Biscuit. Friendly. I brought ham." "You brought ham." "Ham's my whole contingency plan." Bill produced, from his jacket pocket, a slice of ham in a sandwich bag, which he held up like a warrant. "Also I've thought about the wall. Six foot, ivy, easy climb, and there's a wheelie bin on our side to give us a leg up." "And on the other side?" "Grass, presumably." "Presumably." "Molly, at some point in every job you have to trust the grass." She sighed and rubbed her eyes. Somewhere in the flat below, someone was playing scales on a recorder, badly, which she chose not to interpret as an omen. "Fine," she said. "But I'm not going in the bouncy castle." "Nobody asked you to go in the bouncy castle." "You did. Twice. Last night, in the pub, you said, and I quote, 'the castle is the perfect staging area.'" "I'd had four pints and a vision," Bill said. "Bring a bin bag. Wear something festive. And Molly?" "What?" "If anyone asks, we're the entertainment."
created_at
"2026-07-25T13:45:33.22Z"
7/25/2026, 1:45:33 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3366
moderation_latency
(null)
generation_time
21478
tokens_prompt
75
tokens_completion
833
native_tokens_prompt
93
native_tokens_completion
1199
native_tokens_completion_images
(null)
native_tokens_reasoning
61
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
0.03044
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsqBkagD3NLaTAo81gX"
is_byok
false
latency
1270
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-1784987133-KOGNd2xwtYwyaPLniIsq"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987133-8KWoXPDzKSNI3yQxNhdD"
upstream_id
"msg_011CdNsqBkagD3NLaTAo81gX"
total_cost
0.03044
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
97.63%
Matches word count
n/a
neededClean
false
words
507
0.00%
Dialogue to Total Word Ratio
Ratio: 65.12%, Deviation: 15.12%
neededClean
false
wordsTotal
516
wordsDialogue
336
48.8143%