NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HJMS4VPCJT1E1CQGKKVR59
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
15.8s
Cost:
$0.019310
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 lowered her binoculars and grimaced at the suburban backyard. Bill meticulously applied tactical clown makeup to his cheeks. "The primary target turns seven today, Bill. Expect feral resistance." Bill adjusted a squeaky red nose with surgical precision. "Thirty guests means thirty boxes of pure, unadulterated plastic gold." He snapped on yellow dishwashing gloves. Molly unfolded a blueprint scribbled in pink glitter crayon. "The loot rests behind the cake. That creates a tactical flaw." She jabbed a finger at a sloppy sketch of frosted sheet cake. "What about the blindfolded lunatic wielding the wooden pinata stick?" Bill wiped cold sweat from his painted forehead, shuddering. "Divert his attention with sugar. If cornered, twist an aggressive balloon poodle." Molly brandished a plastic pump, loading slender latex tubes like shotgun shells. "Understood. What is the contingency if the bouncy castle collapses prematurely?" "We abandon the heavy board games and grab the video consoles." Bill nodded gravely, adjusting his oversized rainbow necktie with solemn professionalism. "No mercy today. We extract every single Lego kit before naptime arrives." She zipped her tactical diaper bag, eyes narrowing beneath glittery rainbow face paint. "Synchronize silly party watches. Operation Little Monster is officially a go, my partner."
created_at
"2026-09-02T17:28:37.796Z"
9/2/2026, 5:28:37 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1590
moderation_latency
(null)
generation_time
15709
tokens_prompt
75
tokens_completion
1683
native_tokens_prompt
67
native_tokens_completion
5136
native_tokens_completion_images
0
native_tokens_reasoning
4857
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
0.01931025
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788370117-bo3ifOJtTnpxGJnFdilA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788370117-z5pNmHQ1scJ39yaHQfsC"
upstream_id
"xVyYavCANsfn_uMPnaGWoQ0"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"xVyYavCANsfn_uMPnaGWoQ0"
is_byok
false
latency
1588
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.01931025
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
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%