NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCTEVVZR8267F9JD63NZVG9
Run Details
Model:
Gemini 3.5 Flash Lite (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1.8s
Cost:
$0.000715
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
98.88%
Dialogue to Total Word Ratio
(details)
63.0208%
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
Bill adjusted his neon pink tutu and glared at the suburban bounce house glistening in the morning sun. "I still say we hit the jewelry store," Bill whispered. Molly checked her clipboard, adjusting a clown nose that kept sliding off her sweaty nose. "Jewelry stores don't have piñatas, Bill, and more importantly, they don't have seventy-two children hopped up on artisanal juice boxes." "We are master criminals. We robbed the Swiss National Bank." "And we spent it all on this ridiculous van. Now focus. The perimeter is guarded by sugar-crazed toddlers." "So what's the vector?" "Diversionary tactics. I'm going to release thirty ferrets into the petting zoo while you hotwire the gift-laden golf cart." "Ferret stampede?" "Ferret stampede." "Classic." "Just don't trip over the miniature unicorn." "I make no promises." Molly patted Bill’s padded shoulder encouragingly, her fake flower squirting a stream of water directly into his left eye. Bill sighed, wiped his face, and readied his lockpicks. This was undoubtedly a new low in their illustrious criminal careers, but rent was due, and Elmo wasn't going to pay it himself.
created_at
"2026-07-25T14:21:54.952Z"
7/25/2026, 2:21:54 PM
model
"google/gemini-3.5-flash-lite-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
341
moderation_latency
(null)
generation_time
1748
tokens_prompt
75
tokens_completion
295
native_tokens_prompt
67
native_tokens_completion
278
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
0.0007151
router
(null)
provider_responses
0
endpoint_id
"6bd8f433-79e1-416c-b407-1772eb796c9a"
id
"g8Zkat61BJfVjMcPprCMuA8"
is_byok
false
latency
339
model_permaslug
"google/gemini-3.5-flash-lite-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-1784989314-kNSi2gDQCNWDEDwHFN9q"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784989314-L4WVoAqQDHcAnjwSkzbm"
upstream_id
"g8Zkat61BJfVjMcPprCMuA8"
total_cost
0.0007151
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
27.17%
Matches word count
n/a
neededClean
false
words
181
98.88%
Dialogue to Total Word Ratio
Ratio: 53.26%, Deviation: 3.26%
neededClean
false
wordsTotal
184
wordsDialogue
98
63.0208%