NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCTANG053XSWKZQXHJ7J9SD
Run Details
Model:
Gemini 3.6 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
5.5s
Cost:
$0.005193
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
1.31%
Dialogue to Total Word Ratio
(details)
0.6557%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 taped to a sparkly pink bicycle helmet. She looked through the bushes at the suburban house. "We strike at fourteen hundred hours," Molly said. Bill chewed on his unlit cigar. "Fourteen hundred? Molly, it is two in the afternoon. Why do you always say it like a budget action movie?" "Because precision is paramount, William. We are invading a fortress." "It’s a bouncy castle, Molly. With a slight tear on the side." "A bouncy castle guarded by twenty sugar-addicted hyperactive toddlers and a clown named Bobo who looks like he’s running from the Feds," Molly snapped, pulling out a laminated blueprint drawn in crayon. "Focus. The target is the mountain of presents on the patio." Bill leaned in, squinting at the drawing. "Is that a dragon guarding the gift table?" "That’s Timmy’s mom. She’s vigilant. We need a diversion." "I could go in there and do a puppet show," Bill suggested. "I’ve been practicing my voice for Sir Reginald the Ostrich." "No puppets, Bill! We discussed this. Puppets draw questions. Questions lead to total tactical collapse. We stick to the flashbangs." Bill frowned. "By flashbangs, you mean the glitter bombs we bought at the dollar store?" "Precisely. When Bobo starts twisting the balloon animals, you toss the glitter into the cake area. The parents will panic about the carpet. In the chaos, I swoop in with the oversized duffel bag and secure the LEGO sets." "What if there are no LEGOs? What if it’s just socks and handmade cards?" "Did you not intercept the birthday boy's letter to Santa?" Molly asked, her eyes narrowing. "Leo is turning six. He’s loaded. His granddad owns a dealership. There is at least one remote-controlled monster truck in that pile, Bill. And it will be ours." Bill sighed, pulling a pair of tiny noise-canceling headphones over his ears. "I still think we should just ask for a goody bag like normal people." "Goody bags are for amateurs, William. We take the entire loot or we go home broke." "We’re already broke. That’s why we’re stealing from a child." "We are reallocating assets!" Molly corrected loudly, shushing him immediately after. "Keep your voice down. The bouncy castle has eyes." "The bouncy castle is shaped like a giraffe, Molly." "And giraffes are notoriously untrustworthy," she insisted, checking her watch. "T-minus two minutes. Do you have the decoy present?" Bill held up a wrapped box containing a single brick. "Ready." "Good. If anyone asks, we are the cool cousins from out of town." "I don't look six, Molly." "Just smile, blend in, and do not touch the juice boxes. They’re laced with sugar." "Roger that," Bill grumbled. "Operation Birthday Baddest is a go." "Never call it that again."
created_at
"2026-07-25T14:19:37.352Z"
7/25/2026, 2:19:37 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
445
moderation_latency
(null)
generation_time
5428
tokens_prompt
75
tokens_completion
715
native_tokens_prompt
67
native_tokens_completion
679
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
0.005193
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"-cVkaqf7Gu6G-8YP4ciLoAo"
is_byok
false
latency
444
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-1784989177-jWqWxdmhsTYXcasZ0PCP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784989177-I3pfuDNDcXiYL5QqYyIJ"
upstream_id
"-cVkaqf7Gu6G-8YP4ciLoAo"
total_cost
0.005193
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
0.00%
Matches word count
n/a
neededClean
false
words
459
1.31%
Dialogue to Total Word Ratio
Ratio: 79.31%, Deviation: 9.31%
neededClean
false
wordsTotal
464
wordsDialogue
368
0.6557%