NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPNY5YD5WJFQT3NFSM5Q04
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.8s
Cost:
$0.011515
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
98.48%
Dialogue to Total Word Ratio
(details)
86.8173%
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 spread the blueprint across the hood of the van, smoothing it with the flat of her palm. It was not, strictly speaking, a blueprint. It was a birthday invitation with a bouncy castle drawn on the back in crayon. Bill leaned in, squinting through the fog of his own breath. The bouncy castle had been rendered by a seven-year-old with limited spatial awareness, so it appeared to be floating above the garden shed, possibly on fire. "That's the perimeter," Molly said. He nodded slowly, the way a man nods when he has understood nothing but resents being told twice. The plan, as he grasped it, involved clowns. Somewhere in the middle there was a piƱata, and somewhere after that a wheelbarrow, and the wheelbarrow was where Bill came in, because Bill was strong and uncomplicated and could carry forty-six wrapped gifts across a lawn without asking questions about the moral architecture of the thing. Molly folded the invitation into her jacket. Beyond the hedge, a man in a rented tiger costume was inflating balloons with a bicycle pump and swearing softly at the sky. "Two o'clock," she said. "Cake time. Nobody watches the loot table during cake." Bill considered this. It was, he decided, the most beautiful sentence he had ever heard.
created_at
"2026-07-25T13:15:52.387Z"
7/25/2026, 1:15:52 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1768
moderation_latency
(null)
generation_time
9681
tokens_prompt
75
tokens_completion
318
native_tokens_prompt
93
native_tokens_completion
442
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
0.011515
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqZv4rjJKHeJjaFgyFB"
is_byok
false
latency
1768
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-1784985352-9ixG6x4ocmtAlDwKvzu2"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985352-s27jEtZHUt0nD3CPqSA0"
upstream_id
"msg_011CdNqZv4rjJKHeJjaFgyFB"
total_cost
0.011515
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
75.16%
Matches word count
n/a
neededClean
false
words
213
98.48%
Dialogue to Total Word Ratio
Ratio: 6.48%, Deviation: 3.52%
neededClean
false
wordsTotal
216
wordsDialogue
14
86.8173%