NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCVMQ70S4A8ZZT1YWPZT1RP
Run Details
Model:
Gemini 3.6 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.3s
Cost:
$0.002463
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
82.08%
Dialogue to Total Word Ratio
(details)
90.3939%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"I'm telling you, Bill, the bounce house is our entry point," Molly whispered, pointing her flashlight at the blueprints. "Are you insane?" Bill hissed. "The toddler patrol is guarding the perimeter. We'll be smeared in peanut butter." "We go through the bounce house, drop through the mesh netting, and grab the loot table." "What about the clown?" "I'll neutralize him with extra squeaky shoes. He won't know what hit him." "Genius," Bill muttered, adjusting his oversized black ski mask. "And the host?" "Distracted by the pinata collapse I scheduled for fourteen hundred hours." "You scheduled a pinata collapse?" "I loosened the rope, Bill. It's called tradecraft." "Fine, but if those kids catch us, I'm throwing you to the sugar-crazed wolves." "Deal. Do you have the tactical trash bags?" "Right here. Double-ply. Reinforced handles." "Excellent. We want every wrapped package in those bags before the cake is cut." "Even the giant plush dinosaur?" Bill asked, holding up his hands. "Especially the dinosaur," Molly said. "That thing's worth fifty bucks on the black market." "I love this plan," Bill grinned. "Let's ruin this seven-year-old's birthday." "For the loot!" Molly cheered softly. "For the loot!" Bill echoed.
created_at
"2026-07-25T14:42:35.372Z"
7/25/2026, 2:42:35 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
570
moderation_latency
(null)
generation_time
3249
tokens_prompt
75
tokens_completion
321
native_tokens_prompt
67
native_tokens_completion
315
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
0.002463
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"W8tkasbSH764sOIP3eeNSA"
is_byok
false
latency
570
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-1784990555-TaMg9O5Hb6fxRCYugiOM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784990555-mRcTD7fC74dK5vWyK22S"
upstream_id
"W8tkasbSH764sOIP3eeNSA"
total_cost
0.002463
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
98.71%
Matches word count
n/a
neededClean
false
words
194
82.08%
Dialogue to Total Word Ratio
Ratio: 83.33%, Deviation: 6.67%
neededClean
false
wordsTotal
198
wordsDialogue
165
90.3939%