NC Bench
Overview
About
Tests
Models
Model
GPT-4.1
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-04-14-01JRTSY9862P8DW1EF10DJVRP5
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: All right, Bill, here’s the plan—unicorn hats on, gummy worms in your pocket, and nobody suspects a thing. Bill: You actually want me to put gummy worms in my pocket? They’ll melt! Molly: Not if your pockets are lined with tinfoil. Bill: Oh, right. Because carrying tinfoil doesn’t scream “I’m a criminal.” Molly: No, it screams “I’m prepared for snacks.” Focus! Bill: Fine. Unicorn hats, tinfoil-lined pockets, walk in like we’re invited. Molly: Absolutely. Head straight for the bouncy castle, act winded, and make the kids laugh. Bill: What about Felicia? She’s six and tried to bite me last time. Molly: Wear gloves. I told you. Gloves are critical. Bill: Got it. Gloves. So, after the bouncy castle? Molly: I’ll start the “Pin the Tail on the Donkey” game as a distraction. You slide the foil-wrapped presents into our loot sack. Bill: Wait, is it suspicious if I’m carrying a loot sack? Molly: Not if you call it a “gift bag.” Bill: And if anyone asks why the bag is rattling? Molly: Say it’s building blocks. Or a maraca. Or you’re musical. Bill: You have answers for everything. Molly: That’s why I’m the brains, Bill. Now grab your unicorn horn.
id
"gen-1744656344-tND7kl44PC2EU35EY5zb"
upstream_id
"chatcmpl-BMJ6PWYLURser0Hb2VI3bmgTmUlUA"
total_cost
0.002734
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:45:51.522177+00:00"
Monday, April 14th, 2025 at 6:45:51 PM GMT+00:00
model
"openai/gpt-4.1-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
434
moderation_latency
129
generation_time
5501
tokens_prompt
68
tokens_completion
324
native_tokens_prompt
67
native_tokens_completion
325
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
0.002734
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
204
0.0000%
Dialogue to Total Word Ratio
Ratio: 7.35%, Deviation: 82.65%
neededClean
false
wordsTotal
204
wordsDialogue
15
49.8722%