NC Bench
Overview
About
Tests
Models
Model
Gemini 3 Flash (Preview)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYXDVBQ953S4FQSC45S2F0C
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
"Check the perimeter, Bill." "The bouncy castle is blocking my line of sight, Molly." "Forget the inflatable dragon. Focus on the target. Is the cake served?" "Not yet. The clown is still failing at balloon animals." "Good. That gives us ten minutes before the sugar crash happens. Do you have the camouflage?" "I’m wearing a tutu and a cone hat. I look like a deranged fairy godmother." "You look invisible. Now, the gift table is guarded by a toddler in a dinosaur suit." "A raptor? Or a T-Rex?" "Does it matter?" "The T-Rex has a limited range of motion, Molly. It’s tactical." "He’s sticky, Bill. That’s the real threat. If he touches the bag, we’re compromised." "I’ll distract him with the juice boxes. You grab the Lego sets and the remote-control jeep." "Leave the clothes. We only want the high-velocity plastic." "What about the giant teddy bear?" "Too much bulk. We need to be aerodynamic when the magician starts his finale." "Is it wrong to steal from a six-year-old?" "He’s getting a pony next year. He’ll survive. Move in on my signal." "Wait, is that a piñata?" "Focus, Bill!" "But it's full of Snickers!"
created_at
"2026-02-08T15:20:25.026727+00:00"
Sunday, February 8th, 2026 at 3:20:25 PM GMT+00:00
model
"google/gemini-3-flash-preview-20251217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1003
moderation_latency
(null)
generation_time
3081
tokens_prompt
61
tokens_completion
273
native_tokens_prompt
67
native_tokens_completion
313
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
usage
0.0009725
router
(null)
provider_responses
0
status
200
is_byok
false
latency
1003
endpoint_id
"6e82f652-2693-4b60-bbe0-7362d6e345f0"
provider_name
"Google AI Studio"
model_permaslug
"google/gemini-3-flash-preview-20251217"
api_type
"completions"
id
"gen-1770564021-ApUHYhimdd6NcGogtMe6"
upstream_id
(null)
total_cost
0.0009725
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
198
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
198
wordsDialogue
198
68.3860%