Model

Gemini 3 Pro (Preview)

Test

Dialogue tags

Scenario

Write 200 words with 50% dialogue

Run ID

2025-11-19-01KACPMN7HC75GJP045WHWH0YG

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

AI
Bill unrolled the stolen blueprints across the diner booth’s sticky formica surface with dramatic flair. It was actually a crudely rendered crayon drawing of the Peterson’s backyard, snatched from their refrigerator earlier. He looked intense, treating the wrinkled paper like the complex schematics for a high-security bank vault. "Target acquisition is fourteen hundred hours," Bill whispered, strictly adjusting his sunglasses. Molly sighed, slowly stirring her lukewarm black coffee to delay looking at him. "The clown arrives at two, Bill. Just say two." "Precision is key. The perimeter is guarded by a Golden Retriever named Buster. He has a weakness for peanut butter." Molly patted her heavy coat pocket. "I bought the chunky kind." Bill nodded solemnly, tracing a gloved finger over a red wax squiggle. "Excellent. The payload is on the picnic table. We extract the gift bags during the piñata frenzy." Molly stared at the markings, rubbing her aching temples. "You realize you are planning a tactical Black Ops insertion into a five-year-old's birthday party?" "These aren't just kids, Molly. They are tiny, sticky surveillance drones. If we get made, we face the ultimate interrogation." "Tantrums," Bill shuddered. "We grab the loot and vanish." "If we get caught?" Bill smirked. "We blame the magician."
created_at"2025-11-19T00:01:49.312345+00:00" Wednesday, November 19th, 2025 at 12:01:49 AM GMT+00:00
model"google/gemini-3-pro-preview-20251117" 
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2457
moderation_latency(null)
generation_time34470
tokens_prompt68
tokens_completion1780
native_tokens_prompt67
native_tokens_completion4618
native_tokens_completion_images0
native_tokens_reasoning4326
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" 
usage0.05555
api_type"completions" 
id"gen-1763510473-wNAryIJ02GQc33gBcYXf" 
upstream_id(null)
total_cost0.05555
cache_discount(null)
upstream_inference_cost0
provider_name"Google AI Studio" 

Evaluation details

Result Evaluator Details Meta Data
95.9868% Matches word count n/a
neededCleanfalse
words208
99.6666% Dialogue to Total Word Ratio
Ratio: 52.40%, Deviation: 2.40%
neededCleanfalse
wordsTotal208
wordsDialogue109
97.8267%