NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Flash Lite
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2025-11-18-01KACP8WREDWY5F7Z65533D83G
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
The aroma of sugar and desperation hung thick in the air. Molly, a woman whose criminal record read like a particularly messy nursery rhyme book, peered through the slightly grubby window. “Right, Bill, this is it. Operation ‘Santa’s Little Helpers’.” Bill, whose primary skill was looking perpetually confused, grunted. “You sure about this, Mol? Little Timmy looks like he bites.” “Nonsense. He’s just pre-caffeinated. Now, the target is that enormous pile of wrapped joy. The bigger the bow, the bigger the payday. Remember the plan: distraction is key. You go in there, tell them you’ve seen a unicorn outside. Guaranteed chaos.” “A unicorn? Really?” Bill’s eyes widened. “Will it have glitter?” “Probably. Just make it convincing. I’ll be inside the bouncy castle, disguised as a rogue balloon. Once you’ve got them looking skyward, I’ll be making my exit with the goods. Simple, effective, and utterly brilliant.” Molly winked, a glint in her eye that had nothing to do with birthday candles.
created_at
"2025-11-18T23:54:50.09944+00:00"
Tuesday, November 18th, 2025 at 11:54:50 PM GMT+00:00
model
"google/gemini-2.5-flash-lite"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
197
moderation_latency
(null)
generation_time
1315
tokens_prompt
68
tokens_completion
228
native_tokens_prompt
67
native_tokens_completion
239
native_tokens_completion_images
0
native_tokens_reasoning
0
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
0.0001023
api_type
"completions"
id
"gen-1763510088-Xk8eDGUy8D0uUoYoCRTy"
upstream_id
(null)
total_cost
0.0001023
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
161
0.0000%
Dialogue to Total Word Ratio
Ratio: 63.98%, Deviation: 53.98%
neededClean
false
wordsTotal
161
wordsDialogue
103
0.0000%