NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HGM0CPTMQYV1207EKKFPEQ
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
17.6s
Cost:
$0.024733
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
78.33%
Dialogue to Total Word Ratio
(details)
89.1665%
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
"The bounce house inflates at noon, Molly. That gives us a twenty minute window while all the parents fight over artisanal cupcakes," Bill whispered. "Are you seriously wearing a squeaky red clown nose, Bill?" "It is tactical camouflage, Molly." "It honks whenever you blink." "Forget the nose! Little Timmy’s grandmother shipped a titanium crate from Zurich. Rumor says mint condition vintage space LEGOs." "The mythical monorail set?" Molly gasped. "The very same. Pure black market gold." "Sweet mother of plastic. Where are the loot sacks?" "Disguised as giant papier-mache donkey pinatas. We blend right in." "Brilliant. What about the backyard security?" "One narcoleptic golden retriever and a sugar-crazed toddler named Buster who bites kneecaps." "I brought extra pepper spray." "For the dog?" "For Buster. He is an absolute menace on two legs." "Did you arrange the primary distraction?" Molly asked. "I unleashed three caffeinated ferrets into the ball pit." "Diabolical. Now, we breach through the hedge, sweep the table, ditch the macaroni cards, and exfiltrate over the cedar fence before the balloon artist finishes." "What happens if the magician spots us?" "I bribed the magician, Molly. He is our getaway driver." "Bill, you magnificent idiot, let us go rob Timmy."
created_at
"2026-09-02T16:53:15.294Z"
9/2/2026, 4:53:15 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2040
moderation_latency
(null)
generation_time
17546
tokens_prompt
75
tokens_completion
2001
native_tokens_prompt
67
native_tokens_completion
6582
native_tokens_completion_images
0
native_tokens_reasoning
6267
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
0.02473275
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788367995-nw2dxQjLbuvQOXgKTV0h"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788367995-K5gVZd3PA1s91cwac562"
upstream_id
"e1SYaszYFsOw1MkPwv-RmAE"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"e1SYaszYFsOw1MkPwv-RmAE"
is_byok
false
latency
2039
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.02473275
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
78.33%
Dialogue to Total Word Ratio
Ratio: 97.03%, Deviation: 7.03%
neededClean
false
wordsTotal
202
wordsDialogue
196
89.1665%