NC Bench
Overview
About
Tests
Models
Model
Claude Opus 4.6
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYX05JWRX9CXVGJ3ZTHW9ZV
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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, anchoring one corner with a juice box she'd swiped from a gas station. The crayon-scribed layout of the Hendersons' backyard looked like it had been drafted by a drunk cartographer, mostly because it had been drafted by Bill, who was both drunk and terrible with crayons. Bill squinted at his own masterpiece, rotating it twice before giving up on orientation entirely. He tapped a purple blob near what might have been the bounce house. "We go in through the side gate during the piƱata. Every kid on that lawn will be swinging blind." Molly studied the timeline she'd assembled from Mrs. Henderson's obsessively detailed Facebook posts. Cake at two. Games at two thirty. Present opening at three. The window was tight, but greed made them nimble. "What about the clown?" she asked, not looking up. "Clown's on our payroll." She raised an eyebrow. Bill had a history of overstating his connections, and his so-called contacts had once included a mall Santa who turned out to be a mannequin. Still, twenty-three wrapped presents sat in that living room, and Molly hadn't worn her lucky sneakers for nothing. She folded the map with surgical precision and nodded.
created_at
"2026-02-08T15:13:03.673903+00:00"
Sunday, February 8th, 2026 at 3:13:03 PM GMT+00:00
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1387
moderation_latency
152
generation_time
9541
tokens_prompt
61
tokens_completion
262
native_tokens_prompt
75
native_tokens_completion
304
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
0.007975
router
(null)
provider_responses
0
id
"5761fcf4-dfc1-43d9-9c0f-ac498e609d2d"
status
200
is_byok
false
latency
1387
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-opus-20260205"
api_type
"completions"
id
"gen-1770563573-nP3sTRkSNtLxeZQzCeYF"
upstream_id
"5761fcf4-dfc1-43d9-9c0f-ac498e609d2d"
total_cost
0.007975
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
90.4837%
Matches word count
n/a
neededClean
false
words
210
0.1037%
Dialogue to Total Word Ratio
Ratio: 26.19%, Deviation: 16.19%
neededClean
false
wordsTotal
210
wordsDialogue
55
45.2937%