NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPWCJNZZT6A0V4EHX7JKEK
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.2s
Cost:
$0.011290
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
73.03%
Dialogue to Total Word Ratio
(details)
86.5148%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 hood of the van, though calling them blueprints was generous — she'd sketched the layout of the Pemberton backyard on the back of a pizza menu, complete with a bouncy castle rendered as a lopsided rectangle labeled DANGER ZONE. Bill leaned in, chewing the last of a sausage roll he'd bought at the petrol station forty minutes ago and had been rationing ever since. Crumbs snowed onto the paper. Molly brushed them off with the patience of a woman who had worked with him for eleven years. "Piñata's the distraction," she said. He nodded slowly, as though this were tactical wisdom passed down through generations of criminals rather than something she'd invented in the shower that morning. The presents, she explained with her finger tracing a route past the trestle table, would be stacked beneath the gazebo, unguarded except by grandparents, and grandparents were slow. Bill wrote *GRANDPARENTS = SLOW* in his notebook, underlining it twice. Somewhere beyond the hedge, thirty children shrieked in unison, a sound like a kettle boiling in hell. Bill flinched. "You scared?" He considered the question honestly, watching a balloon drift skyward, and decided that yes, deeply, he was.
created_at
"2026-07-25T13:19:23.737Z"
7/25/2026, 1:19:23 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1611
moderation_latency
174
generation_time
9896
tokens_prompt
75
tokens_completion
313
native_tokens_prompt
93
native_tokens_completion
433
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
0.01129
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqqWLYF8GaBwTM62ZGS"
is_byok
false
latency
1611
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-1784985563-vfWXlpC4xs7uywgJHLfN"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985563-Xc4mmGZahXRLXZUSYe1p"
upstream_id
"msg_011CdNqqWLYF8GaBwTM62ZGS"
total_cost
0.01129
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
199
73.03%
Dialogue to Total Word Ratio
Ratio: 2.51%, Deviation: 7.49%
neededClean
false
wordsTotal
199
wordsDialogue
5
86.5148%