NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCX9J67A7PAPZN0QSM580HC
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
42.9s
Cost:
$0.071733
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
98.69%
Dialogue to Total Word Ratio
(details)
86.9233%
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 handwritten blueprint of Little Timmy grand birthday bouncy castle across the dented hood of their rusted getaway sedan. She pointed a grease stained finger directly at the oversized red box labeled Swingset. "This is ground zero, Bill. The gift table sits right next to the glitter station." Bill adjusted his bright neon pink ski mask, which clashed horribly with his vintage brown tweed suit. He squinted down at the complex map and shook his head with profound professional concern. "Glitter is a tactical nightmare, Molly. It gets everywhere. We will be tracked for weeks." "We strike during the pinata climax. When the pony falls, total chaos reigns supreme." She pulled two warm juice boxes from her vest and tossed one across the hot windshield. Bill caught it clumsily with both hands, nearly dropping his binoculars directly onto the pavement. "Are we completely sure about the cargo? Timmy is getting the Deluxe Lego Death Star." "It is forty thousand pieces of pure street value. We take the Lego and all gift cards." Bill leaned back against the hood, nervously chewing on his thin plastic straw. The relentless afternoon sun beat down, and distant screams of sugar crazed children echoed loudly across the quiet cul de sac. "What about the mother? She looks dangerous. I saw her crush a juice pouch with her hands." "Brenda is a threat, yes. But Clown Shoes Carl is currently on our payroll." "Carl? That complete fool would sell out his own grandmother for a balloon animal." "Precisely. He will create a massive distraction with a giant giraffe while we slip past the perimeter." Molly reached deep into her canvas duffel bag, pulled out two shiny gold party hats, and forcefully snapped one onto Bill head. The tight elastic band pinched his chin, but he adjusted the tall cone with immense dignity. "Do we have a plan if the castle loses air? Panic spreads fast in a deflating structure." "We crawl out through the slide exit and vault the bushes. The car will be idling." "Did you pack any snacks? High sugar crashes could severely ruin our getaway momentum." "I packed six juice boxes and three bags of crackers. We eat on the run." Bill nodded slowly, his eyes wide with nervous adrenaline behind his wool mask. He checked his left wrist, glancing down at a cheap plastic watch that featured a cheerful green dinosaur. "It is exactly fourteen hundred hours. The chocolate cake is being cut right now." "Put on your fake mustache, Bill. It is time to rob an eight year old child." "He will never know what hit him, Molly. Let us move." Molly zipped her heavy tactical jacket, hoisted two empty burlap sacks over her left shoulder, and marched resolutely toward the tall wooden gate. The target was mere feet away, the stakes were delightfully high, and their glorious criminal destiny waited just beyond the flower garden.
created_at
"2026-07-25T15:11:26.929Z"
7/25/2026, 3:11:26 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1478
moderation_latency
(null)
generation_time
42814
tokens_prompt
75
tokens_completion
4020
native_tokens_prompt
67
native_tokens_completion
9551
native_tokens_completion_images
0
native_tokens_reasoning
8940
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
0.071733
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"H9JkasntAfbJ-8YPvOi60Ak"
is_byok
false
latency
1478
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-1784992286-63riKfSHNQt7dyKxZ5hM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784992286-3vzl2Rf5gb5k0GTX0fF6"
upstream_id
"H9JkasntAfbJ-8YPvOi60Ak"
total_cost
0.071733
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
75.16%
Matches word count
n/a
neededClean
false
words
487
98.69%
Dialogue to Total Word Ratio
Ratio: 49.49%, Deviation: 0.51%
neededClean
false
wordsTotal
487
wordsDialogue
241
86.9233%