NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCT0M02R172PTPD61CMXZ72
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
33.5s
Cost:
$0.064810
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
95.34%
Dialogue to Total Word Ratio
(details)
97.6313%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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
Molly spread the blueprint across the grease-stained coffee table. It was a crude crayon drawing of a suburban backyard, complete with a bouncy castle, a weeping clown, and several menacing potted plants. Bill adjusted his heavy night-vision goggles, which were currently useless in the bright afternoon sun leaking through the dusty Venetian blinds. He took a long, tense sip through a tiny plastic straw. Their extensive surveillance stakeout had been utterly brutal, but the glorious birthday payload was simply too massive for two professional thieves to ignore. "Explain the security grid again," Bill said, tapping the crayon drawing. "I do not like the look of this giant inflatable structure at all." "That is the bouncy castle, Bill," Molly whispered, leaning in close over the detailed map. "It holds the south perimeter. Two overly caffeinated mothers guard the wooden gate. If spotted, they will force-feed you gluten-free cupcakes until you pass out." "And the primary target area?" Bill asked, shuddering violently at the thought of baked goods. "A pile of unopened LEGO sets, three video game consoles, and a pony," Molly declared, pointing a ruler at the sunny patio. "The pony is secondary. We focus strictly on the boxed goods." "What about the ankle-biters?" Bill asked, narrowing his eyes behind his dark lenses. "Children are deeply unpredictable, Molly. They lack tactical discipline. One sticky hand on my suit and the operation goes dark." "We use the secret weapon," Molly replied, cracking her knuckles with dramatic flair. "I managed to secure five pounds of raw cotton candy. We deploy the sugar bomb at fourteen hundred hours sharp. While the targets suffer their sugar crash, we move in with sacks." "Brilliant plan," Bill murmured, wiping cold sweat from his brow. "What about the birthday boy? Seven-year-old Timmy is known to be ruthless." "Timmy will be occupied with the pinata," Molly said coldly. "The boy has shockingly terrible spatial awareness. It will take him twenty minutes to hit a papier-mache donkey blindfolded." She slid a pair of yellow rubber dishwashing gloves across the scratched wooden table. Bill stared down at the tactical gear with profound professional respect, slowly slipping them onto his hairy hands. He tested his rubbery grip by snatching a soft plush bear off a nearby wooden dining chair and violently tossing it into the dark hallway behind them. "Do these gloves muffle the sound of tearing wrapping paper?" Bill asked, adjusting his rubber gloves. "They are completely whisper-quiet," Molly promised, smirking. "Now, what is our exit strategy if the clown blows our cover?" "I take out the clown with a pocketful of bright pink glitter," Bill stated firmly. "No witnesses allowed." "Extreme, but necessary," Molly agreed, nodding approvingly at the ruthless tactic. "Remember, we leave no juice box behind. If we pull this off, we will be rich in action figures by dinner." "To suburban piracy and loot," Bill said, raising his juice box in a solemn toast. "To suburban piracy and loot," Molly echoed, clinking her box against his with a dull thump.
created_at
"2026-07-25T14:14:08.137Z"
7/25/2026, 2:14:08 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1329
moderation_latency
(null)
generation_time
33419
tokens_prompt
75
tokens_completion
4057
native_tokens_prompt
67
native_tokens_completion
8628
native_tokens_completion_images
0
native_tokens_reasoning
7963
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
0.0648105
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"sMRkauO1DaLwjrEP_avsiAo"
is_byok
false
latency
1329
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-1784988848-RxXEGcfy7HIGyVwwpCD4"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784988848-fdE2QvvjamI2cTtifnkh"
upstream_id
"sMRkauO1DaLwjrEP_avsiAo"
total_cost
0.0648105
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
99.92%
Matches word count
n/a
neededClean
false
words
503
95.34%
Dialogue to Total Word Ratio
Ratio: 50.98%, Deviation: 0.98%
neededClean
false
wordsTotal
512
wordsDialogue
261
97.6313%