NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCSNBD3DBRNPV644Q71N1ZW
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
13.4s
Cost:
$0.021371
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
"The target is heavily fortified," Molly said, slapping a brightly colored piece of paper onto the table. "We have one window of opportunity between the bouncy castle inflation and the cutting of the cake." Bill leaned over, squinting through his thick glasses. "Molly, this is a Cocomelon themed invitation. It says 'Timmy is Turning Seven!'" "Do not let the primary-colored aesthetics deceive you, Bill. Timmy's parents are hedge fund managers. That pile of presents in the gazebo is worth more than our last three bank jobs combined." "It's a kid's birthday party, Molly. We steal from rich adults, not second-graders." "We are taking back wealth from the next generation," she insisted, tapping a glittery map. "Look at the perimeter. We have two major obstacles: a face-painting station at Alpha point, and a clown named Mr. Sparkles." "Is Mr. Sparkles armed?" "Worse. He has balloon animals and zero situational awareness. If he sees us, he'll try to make us a sword, which will blow our cover. Our entry point is behind the shrubbery. You will wear the inflatable dinosaur suit." Bill stared at her. "I am not wearing the T-Rex costume again. It gets sweaty, and the tiny arms make it impossible to carry loot." "The T-Rex costume provides perfect camouflage amidst thirty screaming kids! They will think you are hired entertainment. While you distract them with a clumsy dance, I slip into the gazebo, bag the LEGO sets, the iPad, and the motorized mini-Ferrari, then disappear." "How am I supposed to dance in that thing without stepping on a toddler?" "Improvise! Do the worm. Kids love the worm." "What about the mother? Mrs. Vance is on the PTA board. I heard she tackled a mailman once." "I have prepared for Mrs. Vance," Molly said, pulling a thermos from her bag. "Organic, non-dairy, sugar-free iced matcha latte. One sip and she’ll be distracted for twenty minutes discussing clean eating." "That's devious." "It's tactical genius, Bill. Now, what is our biggest threat?" "The police?" "No, you idiot. The birthday boy. If Timmy catches us, he will scream. Not a normal scream, Bill. A high-pitched, cake-deprived ultrasonic shriek that will summon every parent in the zip code." "So what do we do if the mark spots us?" "We hand him a juice box and tell him we are secret agents sent by Santa." "Santa doesn't do birthdays, Molly." "He doesn't know that! He's seven! His brain is fifty percent chicken nuggets!" Bill sighed, rubbing his temples. "What's my cut?" "Sixty-forty in my favor, plus you can keep any stray Target gift cards." "Fine. But if I get tackled by a PTA mom, I'm snitching." "Deal. Operation Sugar Rush is a go."
created_at
"2026-07-25T14:07:58.892Z"
7/25/2026, 2:07:58 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1221
moderation_latency
(null)
generation_time
13357
tokens_prompt
75
tokens_completion
1484
native_tokens_prompt
67
native_tokens_completion
2836
native_tokens_completion_images
0
native_tokens_reasoning
2172
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
0.0213705
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"PsNkarWtO4mY-8YPyO7x2Ak"
is_byok
false
latency
1221
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-1784988478-dmWWyvKOWNLAn168ztMQ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784988478-WX3dLyEqcLdVz6KTTCRW"
upstream_id
"PsNkarWtO4mY-8YPyO7x2Ak"
total_cost
0.0213705
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
448
0.00%
Dialogue to Total Word Ratio
Ratio: 90.59%, Deviation: 20.59%
neededClean
false
wordsTotal
457
wordsDialogue
414
0.0000%