NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEAC9FBMECEYBFVXSK73BQ2
Run Details
Model:
Claude Sonnet 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.3s
Cost:
$0.004506
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
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
The warehouse smelled like stale popcorn and desperation, which suited Molly just fine as she spread the blueprints across an overturned crate. Bill leaned over her shoulder, chewing a piece of gum like it owed him money. "So the presents are in the living room," Molly said, tracing a finger along the floor plan she'd swiped from a party planning website. "Guarded by a bouncy castle and, according to my intel, at least four moms with wine." Bill frowned. "Wine moms are the worst kind of security. Unpredictable. Emotional." "Which is why we go in during the piñata." "The piñata?" "Maximum chaos, minimum supervision. Every kid in that backyard will be swinging a stick like it's the apocalypse. Nobody's watching the gift table." Bill nodded slowly, impressed despite himself. He'd worked with amateurs before—people who thought a ski mask and a getaway bike were enough. Molly thought in layers, in distractions, in the beautiful anarchy of seven-year-olds hopped up on sugar. "And if we get caught?" he asked. Molly smiled, folding the blueprint with the precision of a woman who'd done this before. "Then we say we're the clowns." "We don't have costumes." "We will by three o'clock."
created_at
"2026-07-01T07:47:58.582Z"
7/1/2026, 7:47:58 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1473
moderation_latency
(null)
generation_time
8264
tokens_prompt
77
tokens_completion
318
native_tokens_prompt
93
native_tokens_completion
432
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
0.004506
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_0135z6ZQRawVkFffST7Sg2gT"
is_byok
false
latency
1473
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-1782892078-kJKTxcuO8gkVAEIcJeVV"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782892078-jynDneQXZ2aZCQAfoOoc"
upstream_id
"msg_0135z6ZQRawVkFffST7Sg2gT"
total_cost
0.004506
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
0.00%
Dialogue to Total Word Ratio
Ratio: 43.78%, Deviation: 33.78%
neededClean
false
wordsTotal
201
wordsDialogue
88
49.9995%