NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR36P7HQXK1XRXV5XS6534
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.6s
Cost:
$0.013315
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
96.27%
Dialogue to Total Word Ratio
(details)
98.0934%
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
"Balloons," Molly said. "That's our way in." "Balloons." "You'll be the entertainer. Bobo." "Why Bobo?" "Because Reginald doesn't say 'fun,' Bill, it says 'tax fraud.'" "And what are you, then?" "Bobo's assistant. I hold the sack." "The sack of presents." "The sack of presents." "And nobody finds it suspicious that the clown's assistant is walking out with everything the birthday boy owns?" "They'll be watching you fail to juggle." "I can juggle." "You dropped a grapefruit on my foot in March." "That grapefruit was defective." "Two o'clock, garden gate's unlocked, mother's name is Fiona, and the child is called Tarquin." "Tarquin." "Turning seven." "He'll have a bouncy castle, mark my words. Rich ones always do." "So we go in through the bouncy castle." "You don't go in *through* a bouncy castle, Molly, it's not a tunnel, it's an inflatable—" "Fine. We go past the bouncy castle." "Better." "Then out the gate, into the van, and we're in Dover by supper." "And if a child cries?" "Then you honk your nose and I run faster." Bill sighed and reached for the wig. "Fifteen years of crime," he said, "and I've come to this." "Put the shoes on, Bobo."
created_at
"2026-07-25T13:40:35.664Z"
7/25/2026, 1:40:35 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2857
moderation_latency
(null)
generation_time
10512
tokens_prompt
75
tokens_completion
331
native_tokens_prompt
93
native_tokens_completion
514
native_tokens_completion_images
(null)
native_tokens_reasoning
21
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
0.013315
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsTFgMJy55zdUmur2YN"
is_byok
false
latency
1197
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-1784986835-Be9n4xoCKvD566k8T4uv"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986835-XvO8iCdYsDZ9mr4UGIeA"
upstream_id
"msg_011CdNsTFgMJy55zdUmur2YN"
total_cost
0.013315
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
99.92%
Matches word count
n/a
neededClean
false
words
197
96.27%
Dialogue to Total Word Ratio
Ratio: 94.42%, Deviation: 4.42%
neededClean
false
wordsTotal
197
wordsDialogue
186
98.0934%