NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRAGDB585G4Q2SRQMATE0M
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
12.0s
Cost:
$0.015665
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
9.13%
Dialogue to Total Word Ratio
(details)
54.5547%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 blueprint across the hood of the van. It was, technically, a placemat from the Happy Panda Buffet. "Bounce house here," she said, tapping ketchup. "Cake table here. Presents stacked by the piñata, unguarded, roughly forty pounds of wrapped merchandise." Bill squinted. "Forty pounds? Bold estimate." "It's a seven-year-old. Her father owns three car dealerships." "So we're stealing from a child." "We're stealing from a child's *father*, who is insured." Bill unfolded a clown costume, holding it against himself like a bridesmaid dress. "And this is my cover?" "Kids love clowns." "Kids are *terrified* of clowns, Molly. Statistically. There are studies." "Then they'll scatter, and scattering is good for us." He sighed and stepped into the polka-dotted trousers. "What's your cover?" "Aunt Deborah." "Whose Aunt Deborah?" "Everyone's. Every party has one. Nobody questions her, nobody knows who invited her, she takes two slices of cake and leaves." Molly pulled a cardigan from the glovebox and shrugged it on with terrifying ease. "You've thought about this a disturbing amount." "I've been Aunt Deborah at eleven parties." Bill honked his nose, involuntarily, then looked betrayed by it. "Just remember," Molly said, "if anything goes wrong—" "Balloon animals." "Balloon animals," she agreed grimly.
created_at
"2026-07-25T13:44:34.995Z"
7/25/2026, 1:44:34 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4476
moderation_latency
(null)
generation_time
11939
tokens_prompt
75
tokens_completion
398
native_tokens_prompt
93
native_tokens_completion
608
native_tokens_completion_images
(null)
native_tokens_reasoning
51
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
0.015665
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNskuB4rJYGvGMt9NrtB"
is_byok
false
latency
1843
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-1784987075-FtfFfxDbcwgxuav0GGbO"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987075-JVb4FVZYy5mlGCaAqEjm"
upstream_id
"msg_011CdNskuB4rJYGvGMt9NrtB"
total_cost
0.015665
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
99.98%
Matches word count
n/a
neededClean
false
words
202
9.13%
Dialogue to Total Word Ratio
Ratio: 62.44%, Deviation: 12.44%
neededClean
false
wordsTotal
205
wordsDialogue
128
54.5547%