NC Bench
Overview
About
Tests
Models
Model
Claude Opus 4.6
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2026-02-08-01KGYZ7G6TVP60VFJQKZXNBJFG
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 hand-drawn map across the sticky diner table, knocking over a salt shaker. The blueprint looked like it had been sketched by a caffeinated squirrel. "The party starts at two," she said, tapping a crayon-colored rectangle. "That gives us exactly one hour before the piƱata distraction." Bill squinted at the map and turned it upside down. "Why is there a dragon in the backyard?" "That's the bouncy castle, Bill. Focus." He leaned back in the booth, crossing his arms. "I still don't understand why we can't just walk through the front door." "Because Mrs. Henderson checks invitations like a TSA agent with something to prove," Molly hissed. "We go through the side gate, past the garden gnomes, and into the garage where they're staging the gift table." "And the getaway vehicle?" Molly grinned. "Borrowed an ice cream truck. Nobody suspects the ice cream truck." Bill rubbed his temples slowly. "We're stealing presents from eight-year-olds, Molly. This feels like a new low." "It's a new opportunity," she corrected, rolling up the map. "Besides, rich kids get the best stuff. Last year Tommy Parker got a drone." Bill considered this. "I do want a drone." "Everybody wants a drone."
created_at
"2026-02-08T15:52:00.23197+00:00"
Sunday, February 8th, 2026 at 3:52:00 PM GMT+00:00
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1492
moderation_latency
230
generation_time
8618
tokens_prompt
61
tokens_completion
273
native_tokens_prompt
75
native_tokens_completion
318
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
0.008325
router
(null)
provider_responses
0
id
"fa09e62d-1c16-41f2-8ea8-12a0f8748cb2"
status
200
is_byok
false
latency
1491
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-opus-20260205"
api_type
"completions"
id
"gen-1770565910-b9bBos2hCyCvBXXvtFND"
upstream_id
"fa09e62d-1c16-41f2-8ea8-12a0f8748cb2"
total_cost
0.008325
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
203
1.1566%
Dialogue to Total Word Ratio
Ratio: 64.53%, Deviation: 14.53%
neededClean
false
wordsTotal
203
wordsDialogue
131
50.5378%