NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYXXFXPMHBYSJZ78375S88A
Run Details
Model:
Claude Opus 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.4s
Cost:
$0.008225
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
99.30%
Dialogue to Total Word Ratio
(details)
99.0070%
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
Molly spread the hand-drawn map across the hood of the minivan. "Okay, the party starts at two. We go in at two-fifteen, right when the sugar hits." "Why two-fifteen?" Bill asked. "Because that's when they cut the cake. Every adult in that house will be in the kitchen trying to light candles and find a knife that isn't covered in frosting." "Smart. What about the dog?" "There's no dog, Bill." "There's always a dog." "It's a goldfish. Focus. You go through the back sliding door. I'll distract the mom with a clipboard and a fake survey about neighborhood parking." "Parking? Nobody cares about parking." "Suburban moms care about parking more than oxygen. Trust me, I'll have her talking for twenty minutes." "And the presents?" "Piled on a table in the living room. You grab the bag, load everything up, and slip out through the garage." "What if a kid sees me?" "You're wearing a magician costume. Tell them you're making the presents disappear." "That's actually brilliant." "I know. Now, what's our getaway vehicle?" "The minivan." "Perfect. Nothing says invisible like a beige minivan." "This is either genius or deeply sad." "Both, Bill. Always both."
created_at
"2026-02-08T15:29:05.223465+00:00"
2/8/2026, 3:29:05 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2189
moderation_latency
139
generation_time
10189
tokens_prompt
61
tokens_completion
271
native_tokens_prompt
75
native_tokens_completion
314
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
0.008225
router
(null)
provider_responses
0
id
"ef64447e-3ecb-4dd5-ae97-0b312ab9e548"
status
200
is_byok
false
latency
2186
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-opus-20260205"
api_type
"completions"
id
"gen-1770564534-FpMur5fDxX0hrWOwGxQs"
upstream_id
"ef64447e-3ecb-4dd5-ae97-0b312ab9e548"
total_cost
0.008225
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
99.30%
Dialogue to Total Word Ratio
Ratio: 92.89%, Deviation: 2.89%
neededClean
false
wordsTotal
197
wordsDialogue
183
99.0070%