NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-04-14-01JRTSYAE22BJ0FGW34J2HQ0V5
Run Details
Model:
GPT-4.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.7s
Cost:
$0.002574
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3562%
Overall
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, did you get the map? Map? Molly, it’s a bouncy castle and a folding table. Bill, focus. This isn’t just any party. There’s a treasure trove of presents. Gift bags. Wrapping paper. Glitter. I’m not scared of glitter. You will be when it’s stuck in your hair for six months. Now, listen. Phase one: diversion. Cupcake sabotage? Exactly. You drop cupcakes. Chaos ensues. Seems... sticky. That’s the point! Sticky kids, distracted grown-ups. While they’re cleaning, I slip under the table and grab the haul. And if someone sees you? Disguise! Clown wig. No way, Molly. You swore—never again! Desperate times. You know the stakes—we need those water pistols. And the giant teddy bear. Especially the giant teddy bear. Did you pack the sack? Santa-style or laundry hamper? Santa! We’re not amateurs, Bill. Okay, okay. What about the parents stationed by the punch bowl? I’ve got that covered: decoy juice box—full of celery soda. Pure evil. Thank you. On my mark, you launch Operation Cupcake Catastrophe. Copy that. And the piñata? Don’t touch the piñata. But— Last time you smashed it, we spent forty minutes picking candy out of your sock. Fine. Presents only. Agreed. Now, let’s go steal the magic of childhood.
id
"gen-1744656346-LR7dCAAcp2um4FIzohKy"
upstream_id
"chatcmpl-BMJ6QulkoA3tD3QvUsS02ZpWsX9Ss"
total_cost
0.002574
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:45:50.680484+00:00"
4/14/2025, 6:45:50 PM
model
"openai/gpt-4.1-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
362
moderation_latency
148
generation_time
3463
tokens_prompt
68
tokens_completion
304
native_tokens_prompt
67
native_tokens_completion
305
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
0.002574
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
208
wordsDialogue
0
49.3562%