NC Bench
Overview
About
Tests
Models
Model
Claude Opus 4.5
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYZ2T0KMHS2RD9XHKHKQQ2A
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 pressed her face against the chain-link fence, watching the backyard transform into a unicorn-themed nightmare of streamers and inflatable castles. Somewhere beneath that mountain of glittering gift wrap sat their target: thirty-seven presents, conservatively valued at enough money to cover rent and maybe a decent steak dinner. Bill crouched beside her, adjusting his disguise with the confidence of a man who had never successfully disguised himself as anything. The rainbow wig sat crooked on his head, and his face paint made him look less like a cheerful clown and more like a confused zebra having an allergic reaction. She studied the tactical situation. Two exits, one harried mother with wine-glazed eyes, and approximately fifteen sugar-fueled children who would serve as both cover and chaos. The presents had been stacked near the bounce house, guarded only by a golden retriever wearing a party hat. "You remember the plan?" Molly whispered. "Distract the kids, grab the loot, escape through the side gate." "And if something goes wrong?" Bill patted the balloon animal tucked into his waistband. "I make them a giraffe. Nobody suspects the balloon guy." Molly sighed deeply. This was either their greatest scheme or their most embarrassing arrest yet.
created_at
"2026-02-08T15:49:26.432009+00:00"
Sunday, February 8th, 2026 at 3:49:26 PM GMT+00:00
model
"anthropic/claude-4.5-opus-20251124"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1700
moderation_latency
143
generation_time
8569
tokens_prompt
61
tokens_completion
247
native_tokens_prompt
75
native_tokens_completion
295
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
0.00775
router
(null)
provider_responses
0
id
"3c09806f-1447-4f29-b1c8-00b00c4a4fa3"
status
200
is_byok
false
latency
1700
endpoint_id
"de32581c-2e11-4f54-8d29-e8a6e19d3038"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-opus-20251124"
api_type
"completions"
id
"gen-1770565756-Lrt5UaMARj5rdW2lNHiX"
upstream_id
"3c09806f-1447-4f29-b1c8-00b00c4a4fa3"
total_cost
0.00775
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
205
95.4928%
Dialogue to Total Word Ratio
Ratio: 14.63%, Deviation: 4.63%
neededClean
false
wordsTotal
205
wordsDialogue
30
97.4349%