NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCSD4SQ6GT4YY9KV3PA00TK
Run Details
Model:
Gemini 3.6 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
6.1s
Cost:
$0.005846
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
3.62%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
1.8117%
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 adjusted her night-vision goggles, which were currently useless because the sun was beating down on the suburban cul-de-sac. "Are you absolutely certain about this?" Bill asked, nervously adjusting his oversized, pastel clown shoes. "For the hundredth time, yes," Molly snapped. "Timmy Turnblatt’s parents are venture capitalists. The kid is turning six and his haul is worth thousands." "I just feel weird robbing a bouncy castle," Bill muttered. "We aren't robbing the castle," Molly corrected. "We are liberating high-end electronics from the designated gift area." "What if there's a guard dog?" "The only canine on site is a geriatric Chihuahua named Mr. Sprinkles." "Chihuahuas are vicious, Molly!" Bill squeaked. "They have no soul!" "Focus, Bill. What’s the perimeter situation?" Bill pulled out a plastic telescope. "I see three hyperactive kids eating blue cake, a terrified magician, and a dad who has completely checked out." "Excellent. We strike during the piñata assault." "Why then?" "Maximum chaos, Bill. The blindfolded children will be wielding wooden bats like mini berserkers. Nobody will notice two extra adults slipping into the garage." Bill checked his oversized pockets. "I brought the smoke bombs." "Are those actual smoke bombs or bath bombs?" Molly asked, eyeing the pink spheres. "Lavender scented," Bill said defensively. "They relax the enemy!" "We don't want to relax them, we want to rob them!" "Well, lavender calms me down when I’m committing a felony against a toddler!" Molly rubbed her temples. "Did you pack the burlap sacks?" "I couldn't find burlap," Bill confessed. "I brought pillowcases instead." "Pillowcases?" "They have Elsa from Frozen on them. It’s thematic!" "Bill, we are professional thieves, not slumber party attendees." "Elsa is cool, Molly. Literally!" "Shut up. Look, the clown is blowing up a balloon giraffe. That’s our cue." "Wait, I need to check the inventory list again." "PlayStation 5, drone, miniature electric Mercedes," Molly recited quickly. "Now put your mask on." Bill pulled a glittery eye mask over his face. "How do I look?" "Like a confused superhero at a disco. Let's go." They ducked behind the manicured hedge, crawling toward the backyard gate. "My knee popped," Bill whispered loudly. "Shh! You're going to blow our cover!" "I'm thirty-four, Molly, my joints have sound effects!" "If you ruin this payday, I'm leaving you in the ball pit." "You wouldn't dare." "Try me. Now, grab the Mercedes." Bill peeked through the wooden fence slating. "Molly, we have a major problem." "What is it? The dad?" "No," Bill whimpered. "Mr. Sprinkles is blocking the driveway, and he looks thirsty for blood." Molly looked at the tiny dog, who was currently asleep in a patch of sunlight. "He's unconscious, Bill." "It's a trap! He’s lulling us into a false sense of security!" "We are doing this," Molly declared, unlatching the gate. "For the loot!" "For the Elsa pillowcases!" Bill yelled, charging forward entirely too loudly.
created_at
"2026-07-25T14:03:30.167Z"
7/25/2026, 2:03:30 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
464
moderation_latency
(null)
generation_time
5725
tokens_prompt
75
tokens_completion
787
native_tokens_prompt
67
native_tokens_completion
766
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
0.0058455
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"MsJkasCIE-Wl_uMP7NCC2Q4"
is_byok
false
latency
464
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-1784988210-YN8rZAejoo8KGQa3V35W"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784988210-NpoQqnc32qvmDQhUVJCO"
upstream_id
"MsJkasCIE-Wl_uMP7NCC2Q4"
total_cost
0.0058455
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
3.62%
Matches word count
n/a
neededClean
false
words
476
0.00%
Dialogue to Total Word Ratio
Ratio: 73.60%, Deviation: 23.60%
neededClean
false
wordsTotal
481
wordsDialogue
354
1.8117%