NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZV431XRK6B3E89JXBT747Z
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
15.2s
Cost:
$0.027265
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
17.5015%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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 unrolled the blueprint across the sticky diner table, narrowly avoiding a puddle of syrup that had been waging a slow war against the laminate since Tuesday. Bill leaned in, squinting at the floor plan of what appeared to be a suburban split-level with a bounce house penciled into the backyard. "It's Tyler Pemberton's eighth birthday," Molly said, tapping the page. "Forty-seven RSVPs. We're looking at a minimum of forty-seven presents, plus the grandparents, plus the divorced dad overcompensation bonus." Bill scratched his stubble. "I don't know, Moll. Robbing kids feels like a line." "We're not robbing kids. We're robbing the concept of kids." "That's not better." She pushed a napkin toward him, on which she'd sketched, in surprisingly detailed crayon, a man in a bear costume. Bill's face fell. "Absolutely not." "You'd be the entertainment. Nobody suspects the entertainment." "I'm allergic to polyester." "You're allergic to commitment." Bill ignored this and turned the blueprint ninety degrees, which did not help. The bounce house, now on its side, looked vaguely threatening. Outside the diner window, a minivan full of children screamed past, and both thieves flinched in unison, an instinct honed by decades of avoiding school zones and PTA bake sales. "Cake comes out at three," Molly continued. "Presents at three-thirty. That's our window. While they're singing, I slip in through the side gate dressed as Aunt Karen—" "Who's Aunt Karen?" "Every party has an Aunt Karen. It's the law." "And me?" "You distract the parents with a magic trick." Bill stared at her. "I don't know magic." "You know the one with the quarter." "That's not magic, that's just me dropping a quarter." "They'll be three mimosas deep. They'll think it's David Blaine." He sighed and stirred his coffee, which had gone cold somewhere around the mention of the bear costume. A part of him, the part that had climbed the fire escape of the Delacroix Museum in the rain, wanted to say no. The other part, the part that had been living off vending machine pretzels for three weeks, was already calculating the resale value of a Nintendo Switch in mint condition. "How do we get the presents out?" Molly smiled. "Piñata." "What about it?" "We hollow out a piñata, stuff the presents inside, and I carry it to the getaway car. Nobody questions a woman with a piñata. It's the perfect shape. Nothing looks suspicious shaped like a donkey." "That is objectively untrue." "Bill. Look at me." She took his hands across the table, avoiding the syrup with the grace of a woman who had done this before. "This is our Everest. This is our retirement. This is forty-seven LEGO sets, minimum." Bill exhaled slowly, considering the bear costume, the quarter trick, and the slow, inevitable arc of his life. Then he nodded, once, like a man accepting his fate. "Fine," he said. "But I'm not wearing the nose."
created_at
"2026-04-24T13:33:30.057Z"
4/24/2026, 1:33:30 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
736
moderation_latency
(null)
generation_time
15069
tokens_prompt
77
tokens_completion
776
native_tokens_prompt
98
native_tokens_completion
1071
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
0.027265
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"07bb6c4a-445e-480e-8537-1c77042c029f"
is_byok
false
latency
736
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-1777037610-UfFyJzN1G65uBmpnhS9k"
session_id
(null)
api_type
"completions"
id
"gen-1777037610-0qX9Zw1G1lNV8cUuPcfE"
upstream_id
"07bb6c4a-445e-480e-8537-1c77042c029f"
total_cost
0.027265
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
35.00%
Matches word count
n/a
neededClean
false
words
482
0.00%
Dialogue to Total Word Ratio
Ratio: 45.38%, Deviation: 15.38%
neededClean
false
wordsTotal
487
wordsDialogue
221
17.5015%