NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRA7TT4DNWGXWCRM52TZVJ
Run Details
Model:
Gemini 3.7 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.2s
Cost:
$0.015305
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
93.94%
Dialogue to Total Word Ratio
(details)
95.7845%
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
"The primary target is heavily fortified behind the bouncy castle," Molly whispered, adjusting her binoculars. "Molly, it is a six-year-old's birthday party." "High-value loot, Bill. Remote-controlled helicopters. Pristine Lego sets. We breach through the doggy door at fourteen hundred hours sharp." "I'm not squeezing through a doggy flap," Bill grunted. "I have severe sciatica." "Do you want that limited-edition Nintendo Switch or not?" "Obviously, but what about the perimeter guards?" "The clown?" "He makes balloon swords, Molly. He is unpredictable. Truly lethal." "Relax. I brought industrial noise-canceling headphones for the screaming toddlers and organic juice boxes to bribe the hyperactive sugar fiends." "Genius. What is the tactical getaway strategy?" "We shove every wrapped gift into the oversized diaper bag, sprint past the papier-mâché pinata, and vault the cedar backyard fence before the magician cuts the ice cream cake." "What happens if the birthday boy's mother spots us?" "We tell her we are the emergency backup entertainment." "Doing what, exactly?" "Interpretive mime dancing. Now synchronize your digital watch. The bouncy castle deflates in precisely ninety seconds, and that is our ultimate extraction window." Bill nodded gravely. "Copy that, partner. We ride for the Legos."
created_at
"2026-09-03T13:46:12.713Z"
9/3/2026, 1:46:12 PM
model
"google/gemini-3.7-flash-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1373
moderation_latency
(null)
generation_time
12076
tokens_prompt
75
tokens_completion
1303
native_tokens_prompt
67
native_tokens_completion
4068
native_tokens_completion_images
0
native_tokens_reasoning
3767
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
0.01530525
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443172-3GccHMpjkVR0eLi0mhxx"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443172-UZXdzRaaeRitF1Je45L1"
upstream_id
"JHqZap7mNbrv_uMPptax8AY"
provider_responses
0
endpoint_id
"dd072012-3274-417d-97e3-e290cba37e31"
id
"JHqZap7mNbrv_uMPptax8AY"
is_byok
false
latency
1373
model_permaslug
"google/gemini-3.7-flash-20260813"
provider_name
"Google AI Studio"
status
200
total_cost
0.01530525
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
93.94%
Dialogue to Total Word Ratio
Ratio: 95.00%, Deviation: 5.00%
neededClean
false
wordsTotal
200
wordsDialogue
190
95.7845%