NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYYZR339RVHDCSHGV3M9D0B
Run Details
Model:
Claude Sonnet 4.5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.9s
Cost:
$0.005205
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
99.35%
Dialogue to Total Word Ratio
(details)
50.1934%
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 peered around the corner at the bouncy castle deflating in the backyard. "This is your big score? A six-year-old's birthday party?" Bill adjusted his fake mustache. "Trust me, these suburban parents go overboard. I'm talking iPads, designer sneakers, probably a pony." "A pony?" "Metaphorically speaking." Molly watched a clown juggle flaming batons near the gift table. "There's a professional entertainer. This complicates things." "That's why I brought these." Bill pulled two red foam noses from his pocket. "Absolutely not." "We blend in as clown assistants, grab the haul during cake time, exit through the hedge. Simple." Molly sighed, snatching a nose. "If we get caught robbing children, I'm testifying against you." "That hurts, partner." They crept toward the party, dodging a sprinkler and three screaming kids hopped up on juice boxes. The gift table sparkled with expensive wrapping paper. "On three," Bill whispered. "One, two—" A small girl tugged Molly's sleeve. "Can you make a balloon animal?" Molly froze. Bill grinned. "She'd love to, sweetheart. Wouldn't you, Giggles?" Molly's eye twitched. "Absolutely thrilled."
created_at
"2026-02-08T15:47:45.234664+00:00"
2/8/2026, 3:47:45 PM
model
"anthropic/claude-4.5-sonnet-20250929"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1537
moderation_latency
131
generation_time
7709
tokens_prompt
61
tokens_completion
271
native_tokens_prompt
75
native_tokens_completion
332
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.005205
router
(null)
provider_responses
0
id
"6de9a0d3-3d99-4168-a72a-4e2b035e8dbf"
status
200
is_byok
false
latency
1535
endpoint_id
"d8bee848-f020-454a-b2be-4a7ce868f99f"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-sonnet-20250929"
api_type
"completions"
id
"gen-1770565656-pimJCScH3zYf1NDTNV7U"
upstream_id
"6de9a0d3-3d99-4168-a72a-4e2b035e8dbf"
total_cost
0.005205
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
1.04%
Matches word count
n/a
neededClean
false
words
174
99.35%
Dialogue to Total Word Ratio
Ratio: 52.84%, Deviation: 2.84%
neededClean
false
wordsTotal
176
wordsDialogue
93
50.1934%