NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8TVT3CZPN6AF942P45DGHN
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.9s
Cost:
$0.006456
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
97.17%
Dialogue to Total Word Ratio
(details)
74.5459%
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
"Right," said Bill, unrolling a crayon drawing onto the table. "This is the floor plan." "Is that drawn in crayon?" said Molly. "I had to blend in at the reconnaissance. I'm not proud of it." "You went to a six-year-old's birthday party to case the joint?" "I ate a lot of cake, Molly. Stay focused." "Fine. What's the entry point?" "Bouncy castle. We go in through the back, past the face painter, and straight to the present table." "Why is there a dragon drawn here?" "That's Gerald. He's the dog. Vicious." "Bill, that's a labradoodle." "He looked at me funny." "Every dog looks at you funny. What about the parents?" "They'll be inside watching that magician. We've got a four-minute window." "A magician? What if he sees us?" "Molly, he's going to be pulling a rabbit out of a hat. He's not watching the garden." "And we just grab everything on the table?" "Everything wrapped. Leave the cards." "We're leaving the cards? That's your moral line? Cards?" "I'm not a monster, Molly." "You're stealing from children." "Wealthy children. Now are you in or not?"
created_at
"2026-02-24T22:03:39.51Z"
2/24/2026, 10:03:39 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
708
moderation_latency
153
generation_time
8674
tokens_prompt
77
tokens_completion
385
native_tokens_prompt
92
native_tokens_completion
412
native_tokens_completion_images
(null)
native_tokens_reasoning
84
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
0.006456
router
(null)
provider_responses
0
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id
"b41cc701-d5ed-49b7-8019-3e9c0fa3d93e"
is_byok
false
latency
699
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771970619-ToPSgzmIkfN9EF7fyC1q"
upstream_id
"b41cc701-d5ed-49b7-8019-3e9c0fa3d93e"
total_cost
0.006456
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
184
97.17%
Dialogue to Total Word Ratio
Ratio: 94.12%, Deviation: 4.12%
neededClean
false
wordsTotal
187
wordsDialogue
176
74.5459%