NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Pro
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-11-18-01KACP50157PEVV1573TVTXKVT
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
Bill unrolled the crayon schematic across the car’s dusty hood. A lopsided sun grinned from one corner. A crude bouncy castle, labeled ‘The Dragon’s Maw,’ dominated the yard. He tapped a stick figure wearing a tragic red nose. “Okay. The mark is six-year-old Timothy. The asset pile sits here, under the piñata. High-risk, high-reward.” Molly squinted, tracing a path past a crudely drawn beagle labeled ‘Buster.’ “And security? His dad, who sells insurance? And what on earth is your primary threat?” “That’s Barnaby the Clown. Biggest threat on site. Constant surveillance. Unpredictable patterns. I have a countermeasure.” From his pocket, he produced a small, inflatable hammer that squeaked pathetically when he squeezed it. “You’re not serious. You’re going to neutralize a professional entertainer with a squeaky hammer?” “Psychological warfare, Molly. It’s what he’ll least expect. We move during the cake-cutting. Maximum sugar-induced distraction.” She eyed the map, where stick figures labeled “US” hid behind a wobbly plastic flamingo. “This is the dumbest plan we have ever had. Truly.” “Financially, perhaps. But in terms of pure, chaotic audacity? It’s a masterpiece.” He beamed, his expression deadly serious.
created_at
"2025-11-18T23:53:07.617196+00:00"
Tuesday, November 18th, 2025 at 11:53:07 PM GMT+00:00
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2053
moderation_latency
(null)
generation_time
26010
tokens_prompt
68
tokens_completion
1188
native_tokens_prompt
67
native_tokens_completion
3400
native_tokens_completion_images
0
native_tokens_reasoning
3111
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
0.03408375
api_type
"completions"
id
"gen-1763509960-DqoMRJHxf51knXWI9gcD"
upstream_id
(null)
total_cost
0.03408375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
192
99.8118%
Dialogue to Total Word Ratio
Ratio: 52.08%, Deviation: 2.08%
neededClean
false
wordsTotal
192
wordsDialogue
100
97.8993%