NC Bench
Overview
About
Tests
Models
Model
Claude Opus 4.5
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYZDQ55CZEXP6M9B45MCF0X
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 target's a seven-year-old's birthday party. Security?" "One grandmother, partially deaf. A golden retriever named Sprinkles who's afraid of balloons." "Balloons we can work with. Entry point?" "Backyard bounce house. We go in through the emergency flap, commando style." "Bill, I'm not fitting through a bounce house flap. I pulled my back stealing those cookies from the Scout troop last month." "Fine. We'll use the garage. The dad leaves it open because he's always forgetting the ice." "Amateur. What about the presents?" "Stacked on a folding table near the cake. We're looking at maybe fifteen, twenty wrapped packages. Could be Legos. Could be socks. High risk, uncertain reward." "That's the game we play. Getaway vehicle?" "My nephew's Power Wheels Jeep." "You're joking." "It's inconspicuous, Molly. Nobody suspects the tiny pink Jeep." "And the distraction?" "I hired a clown." "You hate clowns." "I do. Deeply. But that's what makes it the perfect crime. Who would ever believe I'd work with one?" "This is either genius or we're going to prison for the dumbest reason in criminal history." "Probably both."
created_at
"2026-02-08T15:55:24.181829+00:00"
Sunday, February 8th, 2026 at 3:55:24 PM GMT+00:00
model
"anthropic/claude-4.5-opus-20251124"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1661
moderation_latency
191
generation_time
9031
tokens_prompt
61
tokens_completion
274
native_tokens_prompt
75
native_tokens_completion
335
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
0.00875
router
(null)
provider_responses
0
id
"358e8b2f-cc08-4e69-b178-82ecd13232c7"
status
200
is_byok
false
latency
1660
endpoint_id
"de32581c-2e11-4f54-8d29-e8a6e19d3038"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-opus-20251124"
api_type
"completions"
id
"gen-1770566114-mMbOT9vDKpUx4YTbShr5"
upstream_id
"358e8b2f-cc08-4e69-b178-82ecd13232c7"
total_cost
0.00875
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
192
96.7278%
Dialogue to Total Word Ratio
Ratio: 94.27%, Deviation: 4.27%
neededClean
false
wordsTotal
192
wordsDialogue
181
96.3573%