NC Bench
Overview
About
Tests
Models
Model
Claude Sonnet 4.5
Test
Dialogue tags
Scenario
Write 500 words with 30% dialogue
Run ID
2026-02-08-01KGYWXXVHF9E4VCNQSYSY2GKQ
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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 pressed her back against the colorful bounce house, its inflatable castle towers wobbling with each gust of wind. She pulled out a crumpled napkin with a hastily drawn map of the backyard. "This is absolutely ridiculous," Bill whispered, adjusting his oversized sunglasses. A balloon drifted past his head, and he swatted it away nervously. "You said you wanted easy money. Birthday parties are goldmines." Molly traced her finger along the napkin's crayon marks. "Present table is by the patio. We go in during the piñata." "We're stealing from children, Molly. Children." She shot him a look that could curdle milk. The sound of off-key singing drifted from the yard as twenty sugar-fueled seven-year-olds butchered the birthday song. Molly peeked around the bounce house's corner, observing the battlefield ahead. The present table sat unguarded, wrapped boxes gleaming in the afternoon sun like treasure chests. Parents clustered near the cake, phones out, documenting every moment for posterity. Bill tugged at his collar. Sweat beaded on his forehead despite the mild weather. He'd worn a blazer, which Molly had told him was stupid for a backyard heist, but he'd insisted on looking professional. "What if someone sees us?" Bill asked. "Then we pretend we're looking for the bathroom. Use your brain." The birthday girl, a tiny tyrant in a glittery crown, shrieked with delight as her father hung a papier-mâché unicorn from the pergola. Children began forming a chaotic line, each armed with wild enthusiasm and zero patience. Molly crouched low, her sneakers squeaking against the grass. Bill followed, moving with all the grace of a startled giraffe. They crept along the fence line, using an inflatable pool as temporary cover. The chlorine smell mixed with the sweet scent of frosting made Bill's stomach growl inappropriately. "Shh!" Molly hissed. "That wasn't me talking, that was my stomach!" They reached the hydrangea bush nearest the patio. Three feet from glory. The pile of presents towered magnificently, wrapped in paper featuring cartoon characters and sparkles. Molly calculated they could grab maybe five boxes each before making their escape through the side gate. The first child took a swing at the piñata, missing spectacularly. The crowd of kids erupted in laughter and chaos. Perfect cover. "Now," Molly commanded. Bill hesitated, watching a small boy in a superhero cape trip over his own feet. The kid laughed, unbothered, and got back up. "I can't do this." "What?" "Look at them. They're happy. It's pure." Bill stood up, brushing grass off his knees. "I'm out." Molly stared at him, mouth agape, as Bill walked directly through the party, waving apologetically at confused parents, and disappeared through the front gate. She looked at the presents, then at the children screaming joyfully as candy exploded from the broken unicorn. "Damn it," she muttered, following Bill out.
created_at
"2026-02-08T15:11:56.492834+00:00"
Sunday, February 8th, 2026 at 3:11:56 PM GMT+00:00
model
"anthropic/claude-4.5-sonnet-20250929"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1247
moderation_latency
162
generation_time
15826
tokens_prompt
61
tokens_completion
641
native_tokens_prompt
75
native_tokens_completion
745
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
0.0114
router
(null)
provider_responses
0
id
"cf2d2d4e-333a-416f-96ca-d20ed425d2c6"
status
200
is_byok
false
latency
1245
endpoint_id
"d8bee848-f020-454a-b2be-4a7ce868f99f"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-sonnet-20250929"
api_type
"completions"
id
"gen-1770563499-mRclIrWbSs2pD2NQ5R2n"
upstream_id
"cf2d2d4e-333a-416f-96ca-d20ed425d2c6"
total_cost
0.0114
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
0.2141%
Matches word count
n/a
neededClean
false
words
472
0.0035%
Dialogue to Total Word Ratio
Ratio: 15.68%, Deviation: 14.32%
neededClean
false
wordsTotal
472
wordsDialogue
74
0.1088%