NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-04-16-01JRZYWHVCDKN5SVAR2CMBSKG5
Run Details
Model:
o4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
36.5s
Cost:
$0.016991
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
99.87%
Dialogue to Total Word Ratio
(details)
93.1268%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Dim light filtered through the party tent as Molly crouched behind a deflated bouncy castle. Balloons bobbed in a slow breeze, promising chaos. She checked her mini wrench and tiptoed to the gift table. Bill hovered by the punch bowl, nervously adjusting his black gloves. Cupcakes sat on a tier, frosting glinting like tiny gates to riches. The DJ’s speakers hummed a nursery rhyme remix. They exchanged a quick glance. Molly tapped her watch; time was short. Bill grinned and whispered a thumbs up. The children’s laughter echoed beyond the canvas walls, spurring them forward. Shadows danced around eager gifts. Molly: “Bill, are you certain nobody will catch us mid-swipe?” Bill: “Relax, I’ve disguised myself as a balloon animal delivery guy.” Molly: “You look like a deflated lizard in a floppy hat.” Bill: “At least I’m not wearing glitter bombs in my shoes again.” Molly: “Here’s the plan: you distract with party horns, I grab the gifts.” Bill: “Got it. Once the kids start dancing, I’ll unleash the noisemakers.” Molly: “And what about the cake? We need sugar energy for the getaway.” Bill: “Consider it sampled. Now hurry, reinforcements of hyperactive toddlers are incoming.” Molly: “Afterwards, split the loot and vanish into the night—quietly, please.” Bill: “Four presents each? Perfect.”
id
"gen-1744829302-yJBqwcWeoLqusMkJ9ZPT"
upstream_id
"chatcmpl-BN263MMBF3ZNTyDb6WEtppqVmrml7"
total_cost
0.0169906
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-16T18:48:59.610651+00:00"
4/16/2025, 6:48:59 PM
model
"openai/o4-mini-2025-04-16"
app_id
182717
streamed
true
cancelled
false
latency
32790
moderation_latency
84
generation_time
35972
tokens_prompt
68
tokens_completion
3826
native_tokens_prompt
66
native_tokens_completion
3845
native_tokens_reasoning
3520
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
0.0169906
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
211
99.87%
Dialogue to Total Word Ratio
Ratio: 48.11%, Deviation: 1.89%
neededClean
false
wordsTotal
212
wordsDialogue
102
93.1268%