NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-11-19-01KACR81XJDZMDKAMYG915HEP8
Run Details
Model:
Gemini 3 Pro (Preview)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
16.9s
Cost:
$0.023642
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
0.01%
Dialogue to Total Word Ratio
(details)
47.9993%
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
Molly slapped the architectural blueprints against the dashboard of their rusted van. It was actually a crayon drawing on construction paper, stained with grape juice. "The perimeter is heavily fortified," Molly said, tracing a line of festive bunting with a black-gloved finger. "We have hostiles everywhere. Tweaked out on high-fructose corn syrup." Bill squinted through his tactical binoculars at the manicured suburban lawn. "What’s the payload again?" "Lego sets, Bill. The big boxes. Star Wars. High street value." "Dangerous game," Bill muttered, nervously unwrapping a fruit roll-up. "What about the heavy muscle?" "Sparkles the Clown takes five at fourteen-hundred hours. That’s our window. But watch the mother. She’s got eyes like a hawk and a tactical juice box holster." "And the booby trap?" "The piñata," Molly whispered gravely. "If that donkey breaches before we make entry, it’s a stampede. We’ll be trampled under fifty pairs of light-up Velcro sneakers." Bill shivered audibly. "I barely survived the Chuck E. Cheese job." "Pull it together," she snapped. "We breach the bouncy castle, neutralise the gift table, and extract via the slip-n-slide." "What if the cake comes out early?" "Then may God help us all."
created_at
"2025-11-19T00:29:35.716213+00:00"
11/19/2025, 12:29:35 AM
model
"google/gemini-3-pro-preview-20251117"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2340
moderation_latency
(null)
generation_time
16799
tokens_prompt
68
tokens_completion
904
native_tokens_prompt
67
native_tokens_completion
1959
native_tokens_completion_images
0
native_tokens_reasoning
1661
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
0.023642
api_type
"completions"
id
"gen-1763512158-YYluhB9v15uc4gkV3OJG"
upstream_id
(null)
total_cost
0.023642
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
0.01%
Dialogue to Total Word Ratio
Ratio: 67.34%, Deviation: 17.34%
neededClean
false
wordsTotal
199
wordsDialogue
134
47.9993%