NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-19-01KS0V427PDVT4QTG04Z04P1MT
Run Details
Model:
Gemini 3.5 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
57.1s
Cost:
$0.134686
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 binoculars, staring through the foggy windshield of their stolen dessert delivery van. Beside her, Bill was struggling to squeeze his massive frame into a ridiculous green dinosaur costume. He grunted in frustration as his long tail knocked a cup of silver pens onto the wooden van floorboards. "Why must I wear the reptile suit, Molly? I smell like old polyester and deep shame. Look at me. If those children spot this fake tail, they will tear me apart. They are savages, Molly. Pure savages. They destroyed a brand new castle last week. A bouncy inflatable toy castle!" She ignored his dramatic whining and focused back on the hand drawn map. The target backyard was quiet, but things would change once the guests arrived. She highlighted the critical area with a bright yellow marker and sketched an escape route leading directly over the high wooden neighborhood back fence. "Because toddlers trust friendly dinosaurs, Bill. It is basic psychology. Now pay attention. The cake will be served at exactly three o'clock. When the parents sing, we strike. We will secure the large pile of toys in five minutes flat. We cannot ever leave a single shiny gift behind us!" Bill sighed deeply, causing his giant dinosaur tail to swish across the dusty floor. He adjusted his focus toward the colorful paper map, tracing their designated route with a chubby costume claw. His eyes suddenly narrowed as he noticed a critical detail she had mistakenly overlooked in her final planning. "But what about the security clown, Molly? He has balloon animals and a very loud squeaky horn. He could easily alert the adults if he spots me. Have you prepared some juice boxes for distraction? Toddlers will do anything for juice. It is their weakness. We must use it wisely." She reached down into a heavy cardboard box resting between the two front seats. With a triumphant grin, she pulled out a plastic nerf blaster loaded with bright blue foam darts. She patted the weapon gently and slid three extra sweet juice cartons into her sleek leather coat side pockets. "I am fully prepared for any toddler resistance, my friend. These sweet drinks will pacify them instantly. Now, go check our stealth gear. Do you have the burlap sack? We need plenty of room for that giant LEGO box. If we fail this mission, we face absolute, shameful public ruin!" Bill patted his round belly, making a loud plastic squeak. He held up a giant brown sack triumphantly. Suddenly, the front wooden door of the suburban house swung open. A swarm of excited children ran out onto the green lawn. The target birthday party had officially begun. They were ready. "There is no turning back now, Bill. Put your dinosaur head on and secure your tail immediately. We must go steal those toys. It is showtime, partner. Do not let those kids catch you. Remember, high speed is the absolute key to our grand success. Let us move out now!"
created_at
"2026-05-19T19:24:07.296Z"
5/19/2026, 7:24:07 PM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1465
moderation_latency
(null)
generation_time
56935
tokens_prompt
77
tokens_completion
4282
native_tokens_prompt
67
native_tokens_completion
14954
native_tokens_completion_images
0
native_tokens_reasoning
14354
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
"standard"
usage
0.1346865
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"17gMavq0Hqyd1MkP7oHj2Ao"
is_byok
false
latency
1464
model_permaslug
"google/gemini-3.5-flash-20260519"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer
(null)
request_id
"req-1779218647-sQ978g5Ozrz1ex8RrJMR"
session_id
(null)
api_type
"completions"
id
"gen-1779218647-OdkIMmYnmxNO8DF39WjF"
upstream_id
"17gMavq0Hqyd1MkP7oHj2Ao"
total_cost
0.1346865
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
500
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
250
100.0000%