NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPSB98M5RATBKGX203QRCR
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.5s
Cost:
$0.012015
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
66.26%
Dialogue to Total Word Ratio
(details)
83.1276%
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
"Right, so the bouncy castle's the weak point," said Molly. "The bouncy castle." "Structurally. We deflate it, the whole east lawn becomes a slip-and-slide of screaming children. Chaos. We walk out with the presents." "Molly, there's a clown." "Clowns can't run. It's the shoes." "His name's Bimbo the Magnificent and I've seen him at three birthdays now. He does a thing with doves." "Doves are a distraction, Bill. Doves are what he wants us looking at." "I'm just saying, a man who can produce four doves from a sleeve might have other tricks." "Are you frightened of the clown?" "I'm respectful of the clown." "The presents are stacked on a trestle table by the patio. Eleven of them, one enormous. Probably a trampoline." "We can't fence a trampoline." "We can bounce on a trampoline, Bill. That's the beauty. It's a heist with a retirement plan." "And the mother? Big woman, apron, wooden spoon?" "Deborah. She'll be inside with the cake." "You know her name." "I attended the planning meeting. Posed as a face painter." "You can't paint." "Nobody complained." "A child came out of there looking like a crime scene, Molly." "Tiger," said Molly. "It was clearly a tiger."
created_at
"2026-07-25T13:17:44.11Z"
7/25/2026, 1:17:44 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1574
moderation_latency
(null)
generation_time
9419
tokens_prompt
75
tokens_completion
309
native_tokens_prompt
93
native_tokens_completion
462
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
0.012015
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqi9eQ58f3qUzDGxuEY"
is_byok
false
latency
1570
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-1784985464-NAsjQp5IRdGr9oEvHVI7"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985464-0DOhbcEKOj6zRadEKkLZ"
upstream_id
"msg_011CdNqi9eQ58f3qUzDGxuEY"
total_cost
0.012015
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
66.26%
Dialogue to Total Word Ratio
Ratio: 98.01%, Deviation: 8.01%
neededClean
false
wordsTotal
201
wordsDialogue
197
83.1276%