NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-11-18-01KACP5G7S5N5F2C6P16HYHYXK
Run Details
Model:
Gemini 2.5 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
16.0s
Cost:
$0.017354
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
18.3943%
Overall
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
Messages
Meta
AI
“You see the bouncy castle?” “The big red dragon one? It looks flimsy.” “It’s our insertion point. The adults are distracted by the magician.” “Is he any good?” “Bill. Focus. We go in through the back flap during the ‘sawing a lady in half’ bit. No one will be watching it.” “What if it deflates? I’m not getting trapped under cheap vinyl for a bunch of Legos.” “It won’t deflate. The generator is on our side of the fence. Now, the presents are piled by the cake.” “What kind of cake is it?” “How does that matter?” “Motivation, Molly. If it’s carrot cake, I’m not sure my heart will be in this.” “It’s a superhero cake. Now, you grab the presents, I’ll secure the party bags.” “The party bags? What’s in them? Cheap candy and a plastic spider?” “Probably.” “Score. I love plastic spiders.” “Then get your game face on. The magician is sharpening his saw.” “Finally. Let’s go steal some kid’s birthday.” “That’s the spirit, Bill.”
created_at
"2025-11-18T23:53:13.821615+00:00"
11/18/2025, 11:53:13 PM
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2544
moderation_latency
(null)
generation_time
15926
tokens_prompt
68
tokens_completion
1000
native_tokens_prompt
67
native_tokens_completion
1727
native_tokens_completion_images
0
native_tokens_reasoning
1467
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
0.01735375
api_type
"completions"
id
"gen-1763509977-5yTUYsr7trFOvpMk6SoX"
upstream_id
(null)
total_cost
0.01735375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
167
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
167
wordsDialogue
167
18.3943%