NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPQ9XFMTJYS3WHHFPY18WK
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.7s
Cost:
$0.012265
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.04%
Dialogue to Total Word Ratio
(details)
50.0218%
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 birthday invitation across the diner table like a treasure map. "Two o'clock, Saturday. Forty-seven guests, all under the age of nine." Bill stirred his coffee. "That's not a heist, that's a war crime." "It's redistribution. Do you know what these children get? Ponies. Actual ponies." "I got a sock puppet and pneumonia." "Exactly." She tapped the paper. "The presents pile up on the sunroom table. Unguarded, unsorted, unloved." "There'll be parents." "Parents don't watch presents. Parents watch children. It's an entirely different sightline." Molly slid over a hand-drawn diagram. "You go in as the balloon animal guy." Bill studied it. "I don't do balloon animals." "You do a giraffe." "I do a snake that looks like a giraffe with tragic secrets." "Children can't tell the difference. Meanwhile I'm the aunt nobody recognizes, loading the loot into the stroller." "Whose stroller?" "Ours. We rent a stroller." Bill leaned back, hands behind his head, weighing the arithmetic of it all. "Fine. But if a kid cries, I'm out." "They always cry." "Then I'm out immediately," he said, and reached for the diagram anyway, because the sunroom had two exits and only one of them was on Molly's map.
created_at
"2026-07-25T13:16:37.173Z"
7/25/2026, 1:16:37 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1403
moderation_latency
(null)
generation_time
9616
tokens_prompt
75
tokens_completion
316
native_tokens_prompt
93
native_tokens_completion
472
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
0.012265
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqdDUCM8EtXrzN2ZyEC"
is_byok
false
latency
1403
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-1784985397-zIXVzvKxKBH31cE9hjoX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985397-LXLfl8DfcawazeDLTRpm"
upstream_id
"msg_011CdNqdDUCM8EtXrzN2ZyEC"
total_cost
0.012265
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
100.00%
Matches word count
n/a
neededClean
false
words
199
0.04%
Dialogue to Total Word Ratio
Ratio: 66.67%, Deviation: 16.67%
neededClean
false
wordsTotal
201
wordsDialogue
134
50.0218%