NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCW9A0M4QD2YSVP1A5G3XQC
Run Details
Model:
Gemini 3.6 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.1s
Cost:
$0.002493
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.74%
Dialogue to Total Word Ratio
(details)
50.0609%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 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 pointed at the crinkled blueprint. "We go in during the pin-the-tail-on-the-donkey distraction." Bill chewed his twizzler nervously. "What about the bouncy castle guards?" "Those seven-year-olds are amateurs," Molly snapped, pulling a neon pink balaclava over her ears. "I'll bribe the clown with actual confetti. You secure the haul from the gift table." "Is it mostly Lego?" Bill asked, adjusting his tactical juicebox harness. "Because my pockets are full of sticky fruit snacks." "Focus, Bill! We are after the shiny packages wrapped in dinosaur paper," Molly whispered, scanning the chaotic backyard through her binoculars. "That's where the high-value loot hides." Bill gasped softly. "Do you think there’s a battery-operated monster truck?" "If there is, it's mine," Molly said firmly. "You take the plushies." "No way, I want the remote-control helicopter!" Bill protested loudly, dodging a rogue flying cupcake. Molly grabbed his collar. "Keep it down! You'll alert the birthday boy's mother." "She looks terrifying," Bill whimpered, peeking over the wooden fence. "She's holding a piñata stick." "Then we strike now," Molly commanded, slipping through the latch. "Grab the loot and meet me at the sandbox." "For the toys!" Bill cheered. "For the toys," Molly agreed.
created_at
"2026-07-25T14:53:49.984Z"
7/25/2026, 2:53:49 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
554
moderation_latency
(null)
generation_time
3074
tokens_prompt
75
tokens_completion
331
native_tokens_prompt
67
native_tokens_completion
319
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
0.002493
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"_s1kav3yAYWJ-sAPoN_y8AY"
is_byok
false
latency
554
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-1784991229-xMMG3Vk1jzlUb2Krr3X9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784991229-ERr17WLNcqIA2ccHVuzD"
upstream_id
"_s1kav3yAYWJ-sAPoN_y8AY"
total_cost
0.002493
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
99.38%
Matches word count
n/a
neededClean
false
words
195
0.74%
Dialogue to Total Word Ratio
Ratio: 64.88%, Deviation: 14.88%
neededClean
false
wordsTotal
205
wordsDialogue
133
50.0609%