NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCX0DY7XY3ZDNKPPV5BNFGJ
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
19.3s
Cost:
$0.034263
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
94.75%
Dialogue to Total Word Ratio
(details)
90.5658%
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
Molly adjusted her fake mustache. "Alright, Bill, phase one: disguise as clowns." "I am not wearing the red nose, Molly. It ruins my cheekbones." "Fine, you're the balloon specialist. The target is Timmy's seventh birthday party. The loot consists of three PlayStations, a pony voucher, and twenty cash envelopes from desperate grandparents." "What about security?" "A hyperactive golden retriever and a mother fueled entirely by cheap prosecco." "Terrifying. What is our primary entry point?" "The bounce house at fourteen hundred hours. While the ankle-biters eat cake, you grab the loot near the bouncy castle and throw it over the fence." "And if tactical mothers surround us?" "Deploy the tactical glitter bomb, Bill. They'll spend weeks vacuuming. We escape through the neighbor's hedge, rendezvous at the getaway minivan, and split the Lego." "Is the minivan booster-seat compliant?" "We're thieves, Bill, not monsters. Of course it is." "Good. Did you pack juice boxes?" "Apple and grape. Now pay attention." Molly tapped the tactical map. "Focus, Bill. Twenty tiny screamers stand between us and that mountain of wrapped treasure. Are you in or out?" "I'm in. Let's go rob some unsuspecting seven-year-olds."
created_at
"2026-07-25T15:06:27.663Z"
7/25/2026, 3:06:27 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1409
moderation_latency
(null)
generation_time
19292
tokens_prompt
75
tokens_completion
1614
native_tokens_prompt
67
native_tokens_completion
4555
native_tokens_completion_images
0
native_tokens_reasoning
4258
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
0.034263
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"89BkarmNLJPpjrEP7ai22QE"
is_byok
false
latency
1409
model_permaslug
"google/gemini-3.6-flash-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-1784991987-UC5VwUy89zG7AWU0i9N1"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784991987-SX0EhS6tIHLUT2UNvhod"
upstream_id
"89BkarmNLJPpjrEP7ai22QE"
total_cost
0.034263
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
86.38%
Matches word count
n/a
neededClean
false
words
189
94.75%
Dialogue to Total Word Ratio
Ratio: 94.82%, Deviation: 4.82%
neededClean
false
wordsTotal
193
wordsDialogue
183
90.5658%