NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8TWBWJ5TKASA99A71MKTW3
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.6s
Cost:
$0.006531
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
62.50%
Dialogue to Total Word Ratio
(details)
52.9415%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 bouncy castle is the problem," said Molly, spreading the hand-drawn map across the hood of the van. "Why is the bouncy castle a problem?" "Because I drew it too big and now it's covering the back gate on the map." Bill squinted at the paper. "Is that a clown?" "That's a guard." "It's wearing big shoes." "It IS a clown, Bill. They hired a clown. Every party has a clown." "I hate clowns." "Everyone hates clowns. That's not relevant." Molly tapped the map firmly. "We enter through the side garden at two fifteen, when the singing telegram arrives." "They have a singing telegram too?" "This kid's parents are loaded, Bill. That's why we're here." "How many presents are we talking?" "I counted forty-seven through the binoculars." "You were watching a children's party through binoculars?" "Professionally." "That doesn't make it less weird, Molly." "The point is, forty-seven presents, two of us, one van." She rolled up the map. "We're rich." Bill was quiet for a moment. "What if some of the presents are just socks?" "Then we steal the socks, Bill." "Fair enough."
created_at
"2026-02-24T22:03:57.755Z"
2/24/2026, 10:03:57 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
714
moderation_latency
228
generation_time
8302
tokens_prompt
77
tokens_completion
397
native_tokens_prompt
92
native_tokens_completion
417
native_tokens_completion_images
(null)
native_tokens_reasoning
95
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
0.006531
router
(null)
provider_responses
0
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id
"91273f31-450d-4e34-9db7-5e3637a9da80"
is_byok
false
latency
714
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771970637-2HsnHhgTDscke8yyeEJC"
upstream_id
"91273f31-450d-4e34-9db7-5e3637a9da80"
total_cost
0.006531
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
183
62.50%
Dialogue to Total Word Ratio
Ratio: 81.72%, Deviation: 8.28%
neededClean
false
wordsTotal
186
wordsDialogue
152
52.9415%