NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-11-18-01KACP4KG11XB32PM8FS09HRJV
Run Details
Model:
Gemini 2.5 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
18.3s
Cost:
$0.023504
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
98.56%
Dialogue to Total Word Ratio
(details)
94.5209%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 flattened the blueprints for “Bouncy Castle Bonanza” across the van’s dusty dashboard, a crinkled map to untold riches in LEGO and action figures. Her finger, stained with surveillance coffee, traced the infiltration route. The target zone was a shimmering mountain of brightly wrapped boxes, guarded only by a clown with tragically deflating shoes and a seven-year-old on a tactical sugar high. Bill, meanwhile, had the binoculars trained on the sugar-fueled chaos, a wistful look on his face. He wasn't tracking security; he was watching a frantic game of musical statues. The scent of hot dogs and minor childhood betrayal wafted through their open window. “Focus, Bill. What’s the clown’s status?” He lowered the binoculars. “He’s making a giraffe. I always wanted a balloon giraffe.” Molly jabbed a finger at the schematics. “The presents, Bill. Not the inflatable menagerie.” He sighed, picking up his grappling hook, which was just a coat hanger taped to a jumprope. This was their moment. The clown had just started on the surprisingly intricate tail, his attention completely compromised. This job was almost too easy. They were professionals, after all. Professionals who steal from children.
created_at
"2025-11-18T23:52:46.601659+00:00"
11/18/2025, 11:52:46 PM
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2566
moderation_latency
(null)
generation_time
18240
tokens_prompt
68
tokens_completion
1030
native_tokens_prompt
67
native_tokens_completion
2342
native_tokens_completion_images
0
native_tokens_reasoning
2086
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
0.02350375
api_type
"completions"
id
"gen-1763509947-nEiV76b9qVsBHcTNdEPU"
upstream_id
(null)
total_cost
0.02350375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
190
98.56%
Dialogue to Total Word Ratio
Ratio: 13.47%, Deviation: 3.47%
neededClean
false
wordsTotal
193
wordsDialogue
26
94.5209%