NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HHNN777K9H8GZK29GQWCFQ
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.2s
Cost:
$0.015797
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
65.21%
Dialogue to Total Word Ratio
(details)
82.2945%
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 goes live at two," Molly whispered. "And the security?" Bill asked. "A clown named Bongo. He passes out after balloon animals." "Brilliant. What about the suburban moms?" "Completely distracted by the mimosa bar." "What’s our operational window?" "Exactly six minutes during musical chairs. We bag the entire gift table, slide it down the laundry chute, and vanish into the getaway minivan." "Wait, what about the kid with the laser tag vest?" "Little Timmy? I bribed him with sour worms. He’s our inside man." "You bought off an eight-year-old?" "Professionals have standards, Bill. The primary target is the gold-wrapped box. It's the ultra-deluxe Lego pirate ship." "Understood. I'll secure the hallway in the inflatable dinosaur suit." "No, Bill! The velociraptor squeaks!" "It strikes terror, Molly! Pure psychological warfare against toddlers!" "Just grab the burlap sacks. If any child corners you, tell them you're the official toy inspector." "And if they start weeping?" "Throw string cheese and run." "Did you pack the glitter bombs for emergency cover?" "Two pockets full. Is the getaway driver ready?" "Your cousin Frank is idling behind the sandbox." "Flawless. Let's rob this kindergartener blind." "Synchronize watches. Operation Birthday Bash begins now." "May the pinata have mercy on our souls."
created_at
"2026-09-02T17:11:38.008Z"
9/2/2026, 5:11:38 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1376
moderation_latency
(null)
generation_time
11843
tokens_prompt
75
tokens_completion
1377
native_tokens_prompt
67
native_tokens_completion
4199
native_tokens_completion_images
0
native_tokens_reasoning
3864
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
0.0157965
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788369098-YFMUhdzmiyiJhSLRf5iB"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788369098-hctqYGLTG0Q9KZoTcBIc"
upstream_id
"yliYat_TGLKe1MkPsouJoQo"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"yliYat_TGLKe1MkPsouJoQo"
is_byok
false
latency
1376
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.0157965
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
99.38%
Matches word count
n/a
neededClean
false
words
205
65.21%
Dialogue to Total Word Ratio
Ratio: 98.09%, Deviation: 8.09%
neededClean
false
wordsTotal
209
wordsDialogue
205
82.2945%