NC Bench
Overview
About
Tests
Models
Model
Claude Opus 4.5
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYXJKYB73J8HTY0BWJ35Q00
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 crayon-drawn map across the sticky diner table. "So the party starts at two. We go in through the back door by the bouncy castle." "I still think this is low, even for us," Bill said. "Low? We stole a golden retriever last month." "We returned him. He missed his family." "Focus, Bill. Little Timmy's turning eight, and his parents are loaded. We're talking high-end presents. Maybe a PlayStation." "What's our cover?" "You're Chuckles the Clown. I'm your assistant." "I'm not wearing the nose again." "You're wearing the nose." "It gave me a rash, Molly. A visible rash." "Beauty is pain. Now, the presents will be stacked by the fireplace. You distract the kids with balloon animals while I load up the van." "What if a kid cries?" "Kids always cry at parties. It's basically their job." "And the parents?" "Drunk on sangria by two-thirty. Trust me, I've done reconnaissance." "You went to a children's party alone?" "I wore a disguise." "What disguise?" "Concerned aunt." "We don't even know these people!" "Bill, every family has an aunt nobody recognizes. It's practically science. Now, are you in or out?"
created_at
"2026-02-08T15:23:08.608043+00:00"
Sunday, February 8th, 2026 at 3:23:08 PM GMT+00:00
model
"anthropic/claude-4.5-opus-20251124"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1633
moderation_latency
(null)
generation_time
9982
tokens_prompt
61
tokens_completion
270
native_tokens_prompt
75
native_tokens_completion
326
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
0.008525
router
(null)
provider_responses
0
id
"msg_01AFz6MvqLmz3rYxJeZZGDf1"
status
200
is_byok
false
latency
1633
endpoint_id
"be883404-eb42-4b2d-b6e4-c7daa3aa8d62"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.5-opus-20251124"
api_type
"completions"
id
"gen-1770564177-rZ4EbHuK46P3gdVOwwEF"
upstream_id
"msg_01AFz6MvqLmz3rYxJeZZGDf1"
total_cost
0.008525
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
97.6276%
Matches word count
n/a
neededClean
false
words
193
98.8711%
Dialogue to Total Word Ratio
Ratio: 93.26%, Deviation: 3.26%
neededClean
false
wordsTotal
193
wordsDialogue
180
98.2493%