NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE99DJS86TT2QTES7Z1B3E0
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.6s
Cost:
$0.005146
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
68.90%
Dialogue to Total Word Ratio
(details)
75.0858%
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 kitchen table, jabbing a finger at the crude drawing of a bouncy castle. Bill leaned over, squinting through his reading glasses, unconvinced by the entire operation. "A six-year-old's birthday party, Molly. This is rock bottom." "Presents, Bill. Do you know what parents buy these days? Drones. Tablets. Actual gold-plated Legos, apparently." "We're stealing from children." "We're stealing from Amazon Prime accounts. The children won't even remember by Tuesday." Bill crossed his arms, still skeptical, but Molly could see the greed flickering behind his eyes. "How do we even get past the clown?" "The clown is Debra from accounting. She owes me money. She'll let us in the side door." "And the parents?" "Distracted by a piñata I've rigged to explode early. Chaos, Bill. Beautiful, present-shielding chaos." He sighed, pulling off his glasses, rubbing his temples like a man already regretting tomorrow. "Fine. But I'm not wearing a costume this time." "You're wearing the dinosaur costume." "Molly—" "It has pockets, Bill. Big ones. For presents." He groaned, but reached for the tail already laid out on the chair, defeated by simple, practical villainy.
created_at
"2026-07-01T07:28:55.908Z"
7/1/2026, 7:28:55 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3130
moderation_latency
(null)
generation_time
9535
tokens_prompt
77
tokens_completion
365
native_tokens_prompt
93
native_tokens_completion
496
native_tokens_completion_images
(null)
native_tokens_reasoning
37
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
0.005146
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_011oNwe6pp4mpwzwecV4jmP3"
is_byok
false
latency
1816
model_permaslug
"anthropic/claude-sonnet-5-20260630"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.17.0; linux; x64))"
http_referer
(null)
request_id
"req-1782890935-G6J3qgD1ew5BjKloVGKF"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890935-kHWGjoMf9dcc3zWsdlh5"
upstream_id
"msg_011oNwe6pp4mpwzwecV4jmP3"
total_cost
0.005146
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
81.27%
Matches word count
n/a
neededClean
false
words
188
68.90%
Dialogue to Total Word Ratio
Ratio: 57.81%, Deviation: 7.81%
neededClean
false
wordsTotal
192
wordsDialogue
111
75.0858%