NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE90B3Z6BASM0GMS4SQBN33
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.3s
Cost:
$0.005026
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
45.2419%
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 Bill thought was fitting given their current career trajectory. He spread the blueprints across a card table that wobbled like it had commitment issues. "So the party's at 3 PM," Molly said, tracing a finger along the floor plan of the Hendricks residence. "Bounce house is our blind spot. Nobody watches the perimeter when there's a bounce house." Bill nodded, chewing on a red licorice whip like it owed him money. "And the presents?" "Dining room table. Wrapped like Fort Knox had a baby with Hallmark." "Security?" "One golden retriever named Biscuit. Allegedly ferocious. Actually just wants belly rubs." Bill frowned, the kind of frown that suggested moral complexity had entered a heist that really shouldn't have any. "We're stealing a seven-year-old's birthday presents." "We're liberating consumer goods from an unjust distribution system." "That's the dumbest thing you've ever said." "It's a Barbie Dreamhouse, Bill. There's probably a Malibu Ken in there worth actual money on the collector's market." He considered this. Ken did have a surprisingly robust resale value among a very specific, slightly unsettling demographic. "Fine," Bill said. "But I'm not wearing the clown costume again." "The children will expect a clown." "The children will expect cake, not felonies."
created_at
"2026-07-01T07:23:58.475Z"
7/1/2026, 7:23:58 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4122
moderation_latency
(null)
generation_time
13270
tokens_prompt
77
tokens_completion
361
native_tokens_prompt
93
native_tokens_completion
484
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
0.005026
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01NnNPEkF4myWCJq75jTWuLQ"
is_byok
false
latency
4095
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-1782890638-PkjlpVp3dP3s6e0r72Yt"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890638-Pd4429IzzzwLFXP0b6N2"
upstream_id
"msg_01NnNPEkF4myWCJq75jTWuLQ"
total_cost
0.005026
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
90.48%
Matches word count
n/a
neededClean
false
words
210
0.00%
Dialogue to Total Word Ratio
Ratio: 53.77%, Deviation: 43.77%
neededClean
false
wordsTotal
212
wordsDialogue
114
45.2419%