NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HGQS969T9EWZF5E1RJFVR3
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
14.6s
Cost:
$0.017135
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 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
Crouched behind the overgrown rhododendron bushes, Bill adjusted his oversized novelty sunglasses with surgical precision. Across the manicured suburban lawn, sweet chaos reigned supreme. Seven year old Timmy was currently weaponizing chocolate frosting against an inflatable dinosaur, creating the ultimate tactical diversion. Molly studied their hand drawn blueprints scrawled hurriedly on a greasy paper plate. Operation Sticky Fingers was officially active. Intelligence suggested the mother lode rested on the mahogany dining table, specifically remote controlled drones, colorful wrapped mysteries, and stacked cardboard treasures boasting excessive licensed branding. The perimeter defense was nonexistent, guarded only by half asleep grandmothers sipping lukewarm tea from porcelain mugs. Molly nudged his elbow, pointing toward the chaotic patio. "The clown is completely distracted, so secure the Lego mountain." Bill smirked, patting his bulky canvas vest like a seasoned bank robber facing a maximum security vault. "I packed three oversized diaper bags for the primary haul." He checked his digital stopwatch, waiting patiently for the collective sugar rush to reach critical mass. A rogue golden retriever suddenly breached the wooden fence, snatching a hot dog and successfully luring away the final adult supervision. The path inside was entirely clear, smelling faintly of bubblegum, chaos, and victory.
created_at
"2026-09-02T16:55:19.086Z"
9/2/2026, 4:55:19 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2339
moderation_latency
(null)
generation_time
14533
tokens_prompt
75
tokens_completion
1555
native_tokens_prompt
67
native_tokens_completion
4556
native_tokens_completion_images
0
native_tokens_reasoning
4305
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
0.01713525
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788368119-CqUZTzjFaLCWEFpzGGAu"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788368119-y5BX3hTYYQqPlbnSkXIs"
upstream_id
"91SYatjWCbni_uMP8_7omA8"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"91SYatjWCbni_uMP8_7omA8"
is_byok
false
latency
2338
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.01713525
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: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%