NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ93CAK7M0BK7BXR30NAEXN
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.5s
Cost:
$0.004410
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
73.34%
Dialogue to Total Word Ratio
(details)
86.6307%
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
Molly crouched behind the hedgerow, her black turtleneck already collecting burrs and dead leaves. She had worn this outfit to seventeen heists, and not once had it been warm enough. Bill knelt beside her, holding a hand-drawn map of the birthday venue that looked suspiciously like it had been drawn by a child, mostly because it had been drawn by his nephew Gerald. The target was a sixth birthday party for one Timmy Henderson, whose parents had apparently gone completely overboard with the present situation. Through the kitchen window, Molly could count at least forty wrapped gifts stacked against the wall like a colorful, ribbon-adorned fortress. Bill tapped the map with one sausage-thick finger. "The dog." He said nothing further, apparently satisfied with this contribution. Molly had already accounted for the dog. She had accounted for the bouncy castle attendant, the magician named Incredible Steve, and the grandmother who looked disturbingly alert near the gift table. "Distract the clown," she whispered. Bill nodded gravely, pulling a rubber chicken from his jacket with the quiet dignity of a professional. Whatever else you might say about Bill, he always came prepared for situations requiring rubber poultry.
created_at
"2026-02-18T02:26:15.458961+00:00"
2/18/2026, 2:26:15 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
718
moderation_latency
192
generation_time
7191
tokens_prompt
77
tokens_completion
317
native_tokens_prompt
75
native_tokens_completion
279
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
0.00441
router
(null)
provider_responses
0
id
"400d4089-7b0f-449f-bab4-4c6472136dcf"
status
200
is_byok
false
latency
715
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381567-cRKbLVJwmJsNWeveLBjV"
upstream_id
"400d4089-7b0f-449f-bab4-4c6472136dcf"
total_cost
0.00441
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
73.34%
Dialogue to Total Word Ratio
Ratio: 2.54%, Deviation: 7.46%
neededClean
false
wordsTotal
197
wordsDialogue
5
86.6307%