NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8VRW7CH24E2SWHKW0RFMT4
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.8s
Cost:
$0.010210
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
98.51%
Dialogue to Total Word Ratio
(details)
99.2148%
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 spread the crayon-drawn map across the hood of their dented minivan, smoothing out the wrinkles with her palm. The blueprint had cost them two juice boxes and a firm handshake with a kindergartner named Trevor. "The party starts at three," she said, tapping a wobbly rectangle labeled BOUNCY CASTLE. "That's when the sugar hits. Total chaos. Nobody watches the present table once the piƱata comes out." Bill squinted at the map, turning it sideways. "Is that a dog or a security guard?" "That's Mrs. Henderson. She runs the whole operation from a lawn chair by the cooler." Molly pulled out a pair of oversized sunglasses and a floppy sun hat. "We go in disguised as someone's aunt and uncle. Every party has relatives nobody recognizes." "What if someone asks whose family we belong to?" Bill tugged nervously at his clip-on tie. "We point vaguely and say Craig's. There's always a Craig." Bill nodded slowly, the plan settling over him like a warm blanket of criminal intent. He picked up the empty duffel bag from the back seat. "And the getaway vehicle?" Molly jingled a set of keys. "I hot-wired an ice cream truck." "Brilliant." "I know."
created_at
"2026-02-24T22:19:31.956Z"
2/24/2026, 10:19:31 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1447
moderation_latency
181
generation_time
10589
tokens_prompt
77
tokens_completion
377
native_tokens_prompt
92
native_tokens_completion
390
native_tokens_completion_images
(null)
native_tokens_reasoning
69
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
0.01021
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"c0ada3b6-088e-4916-a0a4-385126a751cd"
is_byok
false
latency
1409
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971571-Sy2cPHYw6oBUl4WsmpdY"
upstream_id
"c0ada3b6-088e-4916-a0a4-385126a751cd"
total_cost
0.01021
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
98.51%
Dialogue to Total Word Ratio
Ratio: 46.50%, Deviation: 3.50%
neededClean
false
wordsTotal
200
wordsDialogue
93
99.2148%