NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRKVP9JVXMZHS46PN29635
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.2s
Cost:
$0.016815
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
10.74%
Dialogue to Total Word Ratio
(details)
54.1821%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 unrolled the blueprint across the hood of the van, smoothing it flat with the heel of her hand. It was, technically, a placemat from the Happy Otter Family Diner, but she had annotated it in three colors of crayon, and she considered that professional enough. Bill studied the layout of the Pemberton back garden: the trestle table, the piƱata, the inflatable turret guarding the northern approach. "The bouncy castle is the weak point," Molly said. He chewed his thumbnail. Twenty-two years in the business, four prisons, one bank vault in Antwerp opened with nothing but patience and a dessert spoon, and now this. He looked at the crayon. He looked at the otter. "We're stealing from a six-year-old." "Correction. From a six-year-old's aunts." Molly tapped the table with a purple stub. "Six aunts. Six wrapped rectangles. Aunts buy tablets, Bill. Aunts buy jewelry for children who lose it in sandboxes." The math was, admittedly, elegant. He hated when the math was elegant. She handed him a foam clown nose and a bag of un-inflated balloons, and he accepted both the way a condemned man accepts breakfast. "Balloons," she said. "Wear the nose."
created_at
"2026-07-25T13:49:41.456Z"
7/25/2026, 1:49:41 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3990
moderation_latency
(null)
generation_time
12077
tokens_prompt
75
tokens_completion
367
native_tokens_prompt
93
native_tokens_completion
654
native_tokens_completion_images
(null)
native_tokens_reasoning
71
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
0.016815
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNt9V9qgFUCFd8TJJko2"
is_byok
false
latency
1260
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-1784987381-00VezJ4LegLsbLqJAypd"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987381-lNankNi4BabTxP58cePV"
upstream_id
"msg_011CdNt9V9qgFUCFd8TJJko2"
total_cost
0.016815
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
97.63%
Matches word count
n/a
neededClean
false
words
193
10.74%
Dialogue to Total Word Ratio
Ratio: 22.22%, Deviation: 12.22%
neededClean
false
wordsTotal
198
wordsDialogue
44
54.1821%