NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCY5TG9C9BAYC25MB4EP7E0
Run Details
Model:
Gemini 3.6 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
5.9s
Cost:
$0.004743
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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
Listen up, Bill, Molly whispered, slapping a crumpled floor plan onto the steering wheel. We hit the bounced castle at fourteen hundred hours. Fourteen hundred, Bill repeated, adjusting his clip-on bow tie. Is that before or after the cake? Because I was thinking we could grab a slice. Focus, you idiot, Molly snapped, rolling her eyes. The cake is a distraction. While the birthday girl is blowing out seven candles, we make our move on the pile in the corner. Which pile? The wrapped ones or the gift bags? Bill asked, taking a nervous bite of a stolen juice box. Both, Molly said, pointing a sharp fingernail at a red sticky note on the paper. You deploy the smoke bomb. By smoke bomb, do you mean the vapor rub you put in the humidifier? Bill raised an eyebrow. It’s tactical menthol, Bill! Molly hissed. It’ll cause chaos. The kids will start coughing, the parents will panic about germs, and in the confusion, we swoop. I still think dressing up as glittery clowns is a mistake, Bill muttered, tugging at his polka-dot trousers. My trousers are chafing. You look majestic, Molly lied, checking her fake mustache in the rearview mirror. Now, did you bring the getaway vehicle? I backed the wagon right up to the bushes, Bill said proudly. It’s got brand new rubber wheels. Silent as a mouse. Is it the red Radio Flyer? Molly asked, her eyes narrowing. With the extended sideboards, yes, Bill said, nodding eagerly. It holds three big boxes of Lego and at least four American Girl dolls. Excellent, Molly smirked. What about the guard dog? The golden retriever? Bill grinned. I packed four string cheeses. He’s already compromised. Good man, Molly said, patting his shoulder. What’s our code word if the bouncy castle collapses or a parent catches us? Juice box, Bill offered. No, too common. Make it Macaroni, Molly commanded. Macaroni it is, Bill agreed. What do we do about the kid with the laser pointer? You take him out with the bubble machine, Molly instructed. Blind him with suds. Understood, Bill said, taking a deep breath. Molly, are we really doing this? They’re just children. They have three Playstation fives between them, Bill, Molly said coldly. They don't even appreciate graphics yet. You’re right, Bill gritted his teeth. They’re ungrateful monsters. Let's take those presents. Masks down, Molly ordered, pulling a sequined sleep mask over her forehead. On three. One, two... Wait, Bill yelled. I need to pee. Molly groaned loudly. You had an hour before we left! I was nervous! Bill whined. Fine, Molly snapped. Three minutes. Then we strike.
created_at
"2026-07-25T15:26:52.948Z"
7/25/2026, 3:26:52 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
699
moderation_latency
(null)
generation_time
5657
tokens_prompt
75
tokens_completion
668
native_tokens_prompt
67
native_tokens_completion
619
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
service_tier
"default"
usage
0.004743
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"vdVkapHNFoq4sOIP3qGPkAo"
is_byok
false
latency
699
model_permaslug
"google/gemini-3.6-flash-20260721"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784993213-L2KtoGEdmLg0AR0JcIkO"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784993213-s1QoxWBqAmbbWMc8ZRn6"
upstream_id
"vdVkapHNFoq4sOIP3qGPkAo"
total_cost
0.004743
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
438
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 70.00%
neededClean
false
wordsTotal
440
wordsDialogue
0
0.0000%