NC Bench
Overview
About
Tests
Models
Model
GPT-4.1 Nano
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-04-14-01JRTSZEF0K0JT3VSAT2RVZ0DM
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: "Alright, Bill, hear me out. We snag the gifts, but how do we get in without the kiddies noticing?" Bill: "Easy. We dress as mascot characters. I’ll be the giant panda, you can be a unicorn." Molly: "Brilliant! No one suspects the fluffy giant. But what about the guard dog?" Bill: "Got that covered. I’ll bring a squeaky toy to distract it. Once it’s busy chewing, we slip inside." Molly: "And the presents?" Bill: "Partitioned into two—your bag for the bigger ones, my backpack for the small stuff." Molly: "Have you thought about the alarm? This is a birthday party on the biggest scale." Bill: "I disabled it yesterday. Remember, I reprogrammed the security system—I’m basically a tech wizard now." Molly: "You? I thought you just watched a YouTube tutorial." Bill: "Hey, I learned things! Now, once we grab the loot, how do we leave without the kids chasing us?" Molly: "We dress as clowns and throw confetti. Confuse them long enough to vanish." Bill: "Perfect! This party’s gonna be the best haul we've had." Molly: "Let’s do it. Time to make this the birthday to remember… for all the wrong reasons."
id
"gen-1744656382-PVPjodaBPQ5FGGAbdWMf"
upstream_id
"chatcmpl-BMJ71k4GxMZyArTbxSF8Ki2sdrEKT"
total_cost
0.0001203
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:46:24.568643+00:00"
Monday, April 14th, 2025 at 6:46:24 PM GMT+00:00
model
"openai/gpt-4.1-nano-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
238
moderation_latency
148
generation_time
624
tokens_prompt
68
tokens_completion
284
native_tokens_prompt
67
native_tokens_completion
284
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
0.0001203
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
195
98.7730%
Dialogue to Total Word Ratio
Ratio: 93.33%, Deviation: 3.33%
neededClean
false
wordsTotal
195
wordsDialogue
182
99.0750%