NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Pro
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-11-18-01KACPBF04GW50VHHMXK85G87Y
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
“Okay, the bouncy castle deflates at five.” “That’s our window?” Bill asked, lowering his binoculars. “That’s our window. The parents will be too distracted by the synchronized sugar-crash tantrums. Perfect cover.” “Absolute genius, Molly.” “I know. You go for the side door. I’ll create a diversion with Balthazar the Magnificent.” “Is that the clown?” “He's a magician, Bill. He has a rabbit. Please try to keep up.” “Right. Magician. So, once I'm inside, head straight for the present pile?” “Straight for the pile. Grab anything wrapped in paper with cartoon animals on it. Do not look inside.” “What if I find some really good LEGOs?” Molly sighed, a long, suffering sound. “What?” “The big Star Wars sets. It’d be a real shame to fence a mint-in-box Millennium Falcon.” “You are not keeping a Millennium Falcon for your cat.” “Timmy has very discerning taste!” “Just get the loot. All of it. And for god's sake, if you actually see a pony, leave it.” His eyes widened. “They have a pony? We're robbing a king?” “Get in the house, Bill.”
created_at
"2025-11-18T23:56:36.883917+00:00"
Tuesday, November 18th, 2025 at 11:56:36 PM GMT+00:00
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2498
moderation_latency
(null)
generation_time
23427
tokens_prompt
68
tokens_completion
1121
native_tokens_prompt
67
native_tokens_completion
2933
native_tokens_completion_images
0
native_tokens_reasoning
2656
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
usage
0.02941375
api_type
"completions"
id
"gen-1763510172-GjdH4sOdZvc31jbZ273J"
upstream_id
(null)
total_cost
0.02941375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
27.1658%
Matches word count
n/a
neededClean
false
words
181
99.7371%
Dialogue to Total Word Ratio
Ratio: 92.27%, Deviation: 2.27%
neededClean
false
wordsTotal
181
wordsDialogue
167
63.4515%