NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYYTA8148FRFJNHAEF02RYE
Run Details
Model:
Claude Sonnet 4.5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.7s
Cost:
$0.004785
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
0.09%
Dialogue to Total Word Ratio
(details)
0.5616%
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 pressed her face against the fence, watching balloons bob in the afternoon breeze. "Are you absolutely certain about this?" Bill adjusted his fake mustache nervously. "It's the Henderson kid. Trust me, those presents are loaded." "We're robbing a seven-year-old's birthday party." Molly pulled out binoculars. "Eight-year-old. And yes." "This feels low, even for us." "Remember the yacht job?" She turned to face him. "We need seed money." Bill sighed heavily. "What's the plan?" "I go in as the balloon artist. You're my assistant." "I don't know anything about balloon animals." "Neither do I." Molly grinned. "That's why we'll be terrible at it. While everyone's distracted by our incompetence, you slip inside and grab the haul." "What if there's a real balloon artist?" "Then we're parents who got the address wrong." Bill rubbed his temples. "We're going to jail." "We're going to Bermuda." Molly handed him a bag of uninflated balloons. "Now practice looking artistic." He pulled one out, stared at it helplessly, then looked at Molly. "We're definitely going to jail," he repeated.
created_at
"2026-02-08T15:44:46.90305+00:00"
2/8/2026, 3:44:46 PM
model
"anthropic/claude-4.5-sonnet-20250929"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1998
moderation_latency
185
generation_time
7491
tokens_prompt
61
tokens_completion
251
native_tokens_prompt
75
native_tokens_completion
304
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
0.004785
router
(null)
provider_responses
0
id
"45a07f45-3927-4552-bba2-10e811c85c0c"
status
200
is_byok
false
latency
1997
endpoint_id
"d8bee848-f020-454a-b2be-4a7ce868f99f"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-sonnet-20250929"
api_type
"completions"
id
"gen-1770565478-79ls4nfQrC9kX0tJ2q43"
upstream_id
"45a07f45-3927-4552-bba2-10e811c85c0c"
total_cost
0.004785
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
0.09%
Dialogue to Total Word Ratio
Ratio: 66.29%, Deviation: 16.29%
neededClean
false
wordsTotal
178
wordsDialogue
118
0.5616%