NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPM2A1R0SCCXNSR2YF247G
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.1s
Cost:
$0.013065
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
52.04%
Dialogue to Total Word Ratio
(details)
75.3761%
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
"Presents," said Bill. "Wrapped. Ribboned. Untraceable." "It's a seven-year-old's birthday, Bill." "It's a *vault* with a bouncy castle out front." "What's inside the vault, exactly?" "Toys." "Toys." "Molly, do you know what a limited-edition dinosaur goes for? Sealed?" "No, and neither do you." "I know a man." "You know a man who knows a man who sold you a fake Rolex." "That was a learning experience. Look, we go in at three. Face paint, balloon animals, we blend." "You're forty-six." "I'm youthful." "You'll be the only clown with a lower back brace." "The brace *helps*, structurally, when carrying a sack of gifts." "And the parents? Twenty phones, all filming?" "Parents don't look at other adults. They look at their own child, screaming, on a slide." "That's grim." "That's cover." "And the exit?" "Same door. Everyone hugs the clown goodbye. Nobody frisks the clown." "Somebody will absolutely frisk the clown." "Then we're partners in crime *and* misfortune." "Bill." "Molly." "If we do this, we leave the little girl's present." "Which one's hers?" "The one she opens first, obviously. We watch, we wait, we take the rest." "You're softening." "I'm *scheduling*. Three o'clock. Bring the balloons."
created_at
"2026-07-25T13:14:51.078Z"
7/25/2026, 1:14:51 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1496
moderation_latency
(null)
generation_time
11017
tokens_prompt
75
tokens_completion
325
native_tokens_prompt
93
native_tokens_completion
504
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
0.013065
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqVPeeu56cpWacACCXz"
is_byok
false
latency
1496
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-1784985291-QAcoLexMjvJwAvIhBd2x"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985291-KG0gwxnN9u50y5f24zzK"
upstream_id
"msg_011CdNqVPeeu56cpWacACCXz"
total_cost
0.013065
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
98.71%
Matches word count
n/a
neededClean
false
words
194
52.04%
Dialogue to Total Word Ratio
Ratio: 98.99%, Deviation: 8.99%
neededClean
false
wordsTotal
198
wordsDialogue
196
75.3761%