Model

Gemini 2.5 Flash Lite

Test

Dialogue tags

Scenario

Write 200 words with 90% dialogue

Run ID

2025-11-18-01KACP797TWKGQ0FM4X8ZHZX5C

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

AI
“Right, Bill, you’re sure about this?” Molly whispered, adjusting the fake unicorn horn perched precariously on her head. “Positive. The intel is solid. Free balloons, sugar rushes, and a veritable smorgasbord of… loot,” Bill replied, fumbling with a bright pink noisemaker. “Loot? It’s just toys, Bill. And a lot of sticky little fingers.” “Precisely! The perfect cover. Who’s going to suspect the guy with the suspiciously well-stuffed teddy bear costume of anything untoward?” “You’re wearing a teddy bear costume? I thought we agreed on the clown thing.” “Clowns are too intimidating for kids, Molly. Bears are cuddly. Plus, it helps conceal the crowbar.” “Bill, I can’t believe we’re doing this. Stealing presents from toddlers.” “Think of it as an… early holiday redistribution. Besides, their parents probably bought them too much anyway. We’re providing a valuable service. Now, you distract the bouncy castle. I’ll handle the gift table. Remember, stealth is key. And try not to inhale glitter this time.” “No promises. Just make sure you don’t accidentally hug a child when you go for the big G.I. Joe.” “Duly noted. Operation Joyful pilferage is a go.”
created_at"2025-11-18T23:53:57.38905+00:00" Tuesday, November 18th, 2025 at 11:53:57 PM GMT+00:00
model"google/gemini-2.5-flash-lite" 
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency288
moderation_latency(null)
generation_time1413
tokens_prompt68
tokens_completion274
native_tokens_prompt67
native_tokens_completion290
native_tokens_completion_images0
native_tokens_reasoning0
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/" 
is_byokfalse
finish_reason"stop" 
native_finish_reason"STOP" 
usage0.0001227
api_type"completions" 
id"gen-1763510035-EEX7jtIs9Ak5ZOlhleoD" 
upstream_id(null)
total_cost0.0001227
cache_discount(null)
upstream_inference_cost0
provider_name"Google AI Studio" 

Evaluation details

Result Evaluator Details Meta Data
75.1556% Matches word count n/a
neededCleanfalse
words187
99.9977% Dialogue to Total Word Ratio
Ratio: 89.30%, Deviation: 0.70%
neededCleanfalse
wordsTotal187
wordsDialogue167
87.5766%