NC Bench
Overview
About
Tests
Models
Model
GPT-4.1
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-04-14-01JRTSW8CTW6DWAG64HT3154F6
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
“Bill, listen—what if there’s a bouncy castle? You ever try to look inconspicuous near a bouncy castle?” “Molly, you blend. Bounce a little. Act like you’re watching your kid and stuff.” “I don’t have a kid, Bill.” “Pretend. Everyone’s distracted by cake and sugar crashes. We swoop in.” “Swoop? With all those kids? Last time I swooped, I tripped over a tricycle.” “This is why we did reconnaissance. Table near the clown—not the magician—goes up first.” “What if the clown sees?” “I’ve never seen a clown sober. We’re fine.” “Ok, so what about the presents? You got the bag?” “Double reinforced. Can hold a bicycle or a life-sized flamingo—learned last time.” “Good. Any idea what’s in the presents?” “Does it matter?” “I don’t want another Beanie Baby incident, Bill.” “Trust me, no collectibles this time. Just cheap plastic but in quantity it’s all profit.” “And the parents?” “Distraction. You wear the balloon hat, do the worm.” “Bill, I haven’t done the worm since ’98.” “No one’s sober enough to notice form.” “What if I break something?” “They cheer. Then we run.” “You’re a genius, Bill.” “I know. Grab your wig.”
id
"gen-1744656278-wHWVzMF30X91PsS4fuyP"
upstream_id
"chatcmpl-BMJ5KZjW9QFLD6QTXfVfcFpWobEYc"
total_cost
0.00259
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:44:42.287407+00:00"
Monday, April 14th, 2025 at 6:44:42 PM GMT+00:00
model
"openai/gpt-4.1-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
342
moderation_latency
138
generation_time
2496
tokens_prompt
68
tokens_completion
306
native_tokens_prompt
67
native_tokens_completion
307
native_tokens_reasoning
0
num_media_prompt
(null)
num_media_completion
(null)
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00259
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
195
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
195
wordsDialogue
195
68.0824%