NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR4WNT7EZVP8VHKYVM0473
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.4s
Cost:
$0.012665
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9920%
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 crayon drawing across the hood of the van. "That's the layout. Bouncy castle here, piñata here, and the presents stacked on the folding table by the fence." "You got a seven-year-old to draw us a blueprint?" "I got a seven-year-old to draw us a blueprint for four dollars and a fruit roll-up. She drove a hard bargain." Bill squinted at the paper. "What's this purple thing?" "Clown." "That's a clown?" "That's an *obstacle*," Molly said. "Clowns notice things. Clowns have nothing better to do than notice things. That's their whole job." "So what, I distract the clown?" "You *become* the clown." She dropped a rubber nose into his palm like a getaway key. Bill stared at it. "I have a bad history with noses." "You have a bad history with everything, Bill, that's why you're the wheelman." "Then who's carrying the presents?" "Me. In the piñata." "You're going to hide inside the piñata." "I'm going to *be* the piñata," she said, "and when they hoist me up, I'll be directly above the table." Bill considered this for a long, respectful moment. "And when a child hits you with a stick?" "Then I'll know," Molly said, "that we're on schedule."
created_at
"2026-07-25T13:41:30.945Z"
7/25/2026, 1:41:30 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3300
moderation_latency
(null)
generation_time
10270
tokens_prompt
75
tokens_completion
334
native_tokens_prompt
93
native_tokens_completion
488
native_tokens_completion_images
(null)
native_tokens_reasoning
30
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
0.012665
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsXLerdcE8Y1kSHyPDW"
is_byok
false
latency
1566
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-1784986890-9MiQPpBeJbTgUOCFNbw8"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986890-W38e1i7Ol93egRBZqZod"
upstream_id
"msg_011CdNsXLerdcE8Y1kSHyPDW"
total_cost
0.012665
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
0.00%
Dialogue to Total Word Ratio
Ratio: 77.78%, Deviation: 27.78%
neededClean
false
wordsTotal
207
wordsDialogue
161
49.9920%