NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ95PYTVBYAY4YGN4P5EYVTN
Run Details
Model:
Gemini 3 Flash (Preview, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
19.5s
Cost:
$0.010941
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
72.27%
Dialogue to Total Word Ratio
(details)
86.1270%
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 spread the napkin map. “The bounce house is the kill zone, Bill.” “It’s a seven-year-old’s birthday party, Molly. Try to keep it in perspective.” “Sugar-crazed toddlers are a lethal perimeter defense. We strike during 'Pin the Tail on the Donkey'.” “The classic blindfold maneuver?” “Exactly. While the target is spinning, we swap the gift pile for bags of raw broccoli.” “Broccoli? That’s cold, even for professional thieves.” “It’s a heist, Bill, not a charity gala. Status on the Juice Box Guard?” “Mrs. Higgins? She’s a heavy inhaler of boxed Chardonnay. She’ll be slumped by the pinata by three.” “Perfect. But watch out for the ball pit. It’s a tactical marshland.” “If I lose a shoe in that plastic swamp, I’m retiring. And what about the clown?” “I hired a distraction. ‘Giggles the Unstable’ arrives at two sharp.” “You’re trusting Giggles with our exit strategy?” “He was twenty bucks and brings his own unicycle. Now, the Lego sets are in the North Corner. Avoid the glitter cannons.” “Glitter? That stuff never comes off. I’m wearing a hazmat suit.” “Too bulky. You’ll pop the castle.” “If I go down, tell my mom I died robbing a bank.” “Grab the Pokémon cards and move.”
created_at
"2026-02-25T01:13:14.848Z"
2/25/2026, 1:13:14 AM
model
"google/gemini-3-flash-preview-20251217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1577
moderation_latency
(null)
generation_time
19424
tokens_prompt
77
tokens_completion
1462
native_tokens_prompt
67
native_tokens_completion
3636
native_tokens_completion_images
0
native_tokens_reasoning
3311
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
usage
0.0109415
router
(null)
provider_responses
0
endpoint_id
"6e82f652-2693-4b60-bbe0-7362d6e345f0"
is_byok
false
latency
1577
model_permaslug
"google/gemini-3-flash-preview-20251217"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771981994-vZ15tl4KFeft59Izzj4s"
upstream_id
(null)
total_cost
0.0109415
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
72.27%
Dialogue to Total Word Ratio
Ratio: 97.55%, Deviation: 7.55%
neededClean
false
wordsTotal
204
wordsDialogue
199
86.1270%