NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPWM9TJATWT1836S47Q5Z8
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.0s
Cost:
$0.013015
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
91.12%
Dialogue to Total Word Ratio
(details)
95.5594%
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
"So we're stealing from children," Molly said. "We're stealing from children's *parents*," Bill said. "Big difference. Legally, morally, spiritually." "Explain the spiritual difference." "The presents haven't been opened. Ownership hasn't transferred. It's a gray area." "It's a bouncy castle and a piñata, Bill." "The piñata's full of candy, which we're also taking." "You've thought about this." "I've thought about nothing else since Tuesday. Now, the birthday boy is turning seven. Name's Dominic. Wealthy family, obscene gift table, magician arriving at two." "You're the magician." "I'm the magician." "You don't do magic." "I do one card trick and it fails eighty percent of the time." "And the other twenty?" "It fails differently." "Bill." "Children are easy. You wave a scarf, they scream. Meanwhile you're loading a duffel bag behind the trampoline." "And me? Where am I?" "Face painting." "I can't paint." "Nobody's ever been happy with a face painting. Give them all a lopsided butterfly and they'll cry, and while they're crying—" "—nobody's watching the gift table." "Molly, you're beautiful." "I'm going to hell." "We're going to hell in a car full of Lego, which is the only acceptable way." "Fine. But I want the piñata candy." "Negotiable." "Non-negotiable." "Fine."
created_at
"2026-07-25T13:19:31.649Z"
7/25/2026, 1:19:31 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2289
moderation_latency
(null)
generation_time
10917
tokens_prompt
75
tokens_completion
345
native_tokens_prompt
93
native_tokens_completion
502
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"
service_tier
"default"
usage
0.013015
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqr6GUK9qgBEitNNNki"
is_byok
false
latency
2235
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-1784985571-cDHxbJ7ngYwGBTZVtnWq"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985571-OnWxxKxPLSS8UjkndYRE"
upstream_id
"msg_011CdNqr6GUK9qgBEitNNNki"
total_cost
0.013015
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
100.00%
Matches word count
n/a
neededClean
false
words
200
91.12%
Dialogue to Total Word Ratio
Ratio: 95.52%, Deviation: 5.52%
neededClean
false
wordsTotal
201
wordsDialogue
192
95.5594%