NC Bench
Overview
About
Tests
Models
Model
Claude Opus 4.6
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYYVVMVRVW6CB39VH747A5E
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 sticky diner table, smoothing out the crayon-scribbled edges she'd lifted from the birthday boy's backpack earlier that morning. The layout of the Henderson house was crude but serviceable, complete with a lopsided rectangle labeled PRESENTS HERE in green marker. She tapped it twice with a bitten fingernail. Bill leaned forward, squinting through his reading glasses, which were held together at the bridge with electrical tape. He smelled like cheap aftershave and regret. A french fry dangled from his lip as he studied the diagram, rotating it twice before realizing he'd had it upside down. "The bouncy castle is a problem," Molly said. Bill nodded slowly, the fry bobbing. He'd once been foiled by an inflatable obstacle before, during the infamous Tulsa incident, and the memory still haunted him. "We go in through the garage during cake time," she continued. "Every kid and parent will be in the backyard singing. We grab the gifts, load the van, gone in four minutes." "What about the dog?" "Goldendoodle. Hypoallergenic. Friendly to a fault." Bill finally ate the fry and grinned. The plan was beautiful in its simplicity, criminal in its pettiness, and absolutely worthy of their particular talents.
created_at
"2026-02-08T15:45:39.06603+00:00"
Sunday, February 8th, 2026 at 3:45:39 PM GMT+00:00
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1306
moderation_latency
173
generation_time
9068
tokens_prompt
61
tokens_completion
268
native_tokens_prompt
75
native_tokens_completion
311
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
0.00815
router
(null)
provider_responses
0
id
"683e816a-d5ee-453c-9611-c6c49a505368"
status
200
is_byok
false
latency
1305
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-opus-20260205"
api_type
"completions"
id
"gen-1770565529-eh76auBi9df7eTdUxvpu"
upstream_id
"683e816a-d5ee-453c-9611-c6c49a505368"
total_cost
0.00815
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
204
8.3749%
Dialogue to Total Word Ratio
Ratio: 22.55%, Deviation: 12.55%
neededClean
false
wordsTotal
204
wordsDialogue
46
54.0596%