NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCXEZRJYB25J3ABVEJW5EFF
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
46.5s
Cost:
$0.088271
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
99.9746%
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 slammed a pastel blueprint onto the metal folding table inside their dimly lit basement hideout. She pointed a laser marker at a poorly drawn sketch of a bouncy castle aggressively circled in thick red ink. "Pay attention, Bill. Timmy turns seven at two o'clock today. That gives us a narrow window before the sugar crash sets in." Bill stroked his stubbled chin, squinting at the schematic. He raised an eyebrow at a scribble labeled Threat Level Crimson. "Remind me why we are robbing a second grader again?" Molly leaned across the table, eyes wide with unhinged enthusiasm. She slapped away a crayon that had rolled near her elbows. "Because his father is a crypto billionaire, Bill! The loot on that gift table is astronomical. High end electronics, imported Lego sets, rare video games. We are talking about millions in unmonetized childhood joy." Bill sighed heavily, adjusting his balaclava. He drummed his fingers nervously against a plastic juice box, deep in thought. "I do not know, Molly. Stealing from toddlers feels like a new low, even for us. Remember the catastrophic flamingo heist?" Molly waved her hand dismissively, pacing back and forth across the damp concrete floor of the basement. "The bird was an informant, Bill! Focus! The yard is strictly guarded by a hyperactive mother named Brenda and a hired clown who looks completely unhinged." Bill tapped a pink sticky note attached to the crayon diagram of the inflatable slide. "What is our tactical protocol if the clown goes rogue?" Molly grinned slyly, reaching into her bag to pull out a wooden stick wrapped in colorful crepe paper. "We trigger the piƱata phase. When the wooden donkey bursts, total anarchy ensues. The little monsters will tear each other apart for cheap candy while we strike." Bill nodded in slow, reluctant appreciation. He picked up a pair of giant squeaky shoes sitting beside his bag. "Brilliant. Then we escape through the doggy door?" Molly clicked her pen shut, folding her arms over her chest as she looked at her accomplice. "Precisely. You secure the primary table by the inflatable castle, and I will swiftly sweep the pile near the juice box station." Bill chewed his lip, looking down at his furry disguise. He winced at the thought of bouncing. "What if I get accidentally lured into jumping on that inflatable bouncy castle?" Molly grabbed him firmly by his padded shoulders, staring deeply into his eyes with absolute, terrifying intensity. "You resist the urge, Bill! You are a professional criminal! If anyone asks, we are the entertainment. You are Barnaby the Magic Chimpanzee, and I am your stern handler." Bill put on the rubber monkey mask, his voice sounding completely muffled behind the thick fake snout. "Fine, but I am keeping the tactical glitter bombs ready just in case." Molly smiled darkly, slapping him encouragingly on the back as they moved slowly toward the getaway van. "That is the spirit, Barnaby. If those tiny kids smell fear, they will devour us alive."
created_at
"2026-07-25T15:14:24.674Z"
7/25/2026, 3:14:24 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1271
moderation_latency
(null)
generation_time
46434
tokens_prompt
75
tokens_completion
3765
native_tokens_prompt
67
native_tokens_completion
11756
native_tokens_completion_images
0
native_tokens_reasoning
11100
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
0.0882705
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"0NJkavCPLuf0jrEPhp-ugA0"
is_byok
false
latency
1271
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-1784992464-2Ko9L62d3NxzHwzl6UAK"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784992464-K1brGoN7Ux795scmB0AN"
upstream_id
"0NJkavCPLuf0jrEPhp-ugA0"
total_cost
0.0882705
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
100.00%
Matches word count
n/a
neededClean
false
words
501
99.95%
Dialogue to Total Word Ratio
Ratio: 50.10%, Deviation: 0.10%
neededClean
false
wordsTotal
501
wordsDialogue
251
99.9746%