NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRN7C6ANE956DXY6Y69C7G
Run Details
Model:
Gemini 3.7 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
16.5s
Cost:
$0.021864
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.84%
Dialogue to Total Word Ratio
(details)
99.9201%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 smoothed the architectural blueprint across the sticky diner table, weighing down the corners with salt shakers. Their target was suburban fortress twelve: Timmy Jenkins’ eighth birthday extravaganza. A towering inflatable dragon guarded the perimeter, while an overcaffeinated magician on a unicycle maintained roving surveillance. Bill adjusted his spyglasses, studying the colorful chaos across the street. A mountain of shiny wrapped boxes sat entirely unattended beside the juice bar, practically begging for extraction. The stakes were high; Timmy possessed three unopened Lego sets and a motorized scooter. Molly checked her synchronized stopwatch and leaned across the vinyl booth, her dark eyes narrowed with tactical precision. "The sugar crash hits at precisely three o'clock. That leaves four glorious minutes." Bill nodded grimly, checking his pockets. "I will neutralize the terrifying balloon clown." She smiled, tucking custom smoke bombs shaped like organic juice pouches into her padded tactical vest. They had studied the backyard layout for weeks, mapped sandbox traps, memorized nap times, and bribed catering staff with pudding. Everything rested on speed and avoiding sticky toddler hands in the crowded ball pit. If their cunning distraction held out, they would successfully execute the greatest covert toy heist in modern suburban history.
created_at
"2026-09-03T13:52:12.685Z"
9/3/2026, 1:52:12 PM
model
"google/gemini-3.7-flash-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2036
moderation_latency
(null)
generation_time
16374
tokens_prompt
75
tokens_completion
1642
native_tokens_prompt
67
native_tokens_completion
5817
native_tokens_completion_images
0
native_tokens_reasoning
5567
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
0.021864
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443532-2zWuqXNPZJTPXIckN1d5"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443532-R05fr7xijJrR0RbP0VlQ"
upstream_id
"jHuZaoi5NNf2jMcPwNjzmAc"
provider_responses
0
endpoint_id
"dd072012-3274-417d-97e3-e290cba37e31"
id
"jHuZaoi5NNf2jMcPwNjzmAc"
is_byok
false
latency
2036
model_permaslug
"google/gemini-3.7-flash-20260813"
provider_name
"Google AI Studio"
status
200
total_cost
0.021864
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
100.00%
Matches word count
n/a
neededClean
false
words
200
99.84%
Dialogue to Total Word Ratio
Ratio: 12.00%, Deviation: 2.00%
neededClean
false
wordsTotal
200
wordsDialogue
24
99.9201%