NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ94SR2XTAFTXMMQGK42XYA5
Run Details
Model:
Gemini 3 Flash (Preview, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
37.7s
Cost:
$0.025296
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
99.72%
Dialogue to Total Word Ratio
(details)
98.6722%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 van smelled of stale animal crackers and desperation. Molly smoothed out a hand-drawn map of the backyard, her eyes narrowing as she circled the primary target: a pile of wrapped boxes perilously close to the chocolate fountain. Bill fumbled with his tactical gear, which was mostly just a collection of oversized cargo pockets stuffed with juice boxes and sticky tape. He looked at the blueprint of the bouncy castle, his brow furrowing in deep concentration. To a casual observer, they looked like ambitious suburban parents. To the neighborhood squirrels, they were a menace. The clock was ticking toward cake time. Molly tapped the map with a sharpened crayon, pointing specifically at a suspiciously large gift wrapped in dinosaur paper. The security was tight, consisting mostly of a golden retriever named Sparky and a tired clown who had lied on his resume. They had to be surgical. One wrong move and they would be buried under a mountain of screaming toddlers and party favors. It was the highest-stakes job of their careers. "The bouncy castle is the kill zone," Molly whispered. Bill checked his watch. "I'll handle the clown. He is a quitter."
created_at
"2026-02-25T00:57:17.667Z"
2/25/2026, 12:57:17 AM
model
"google/gemini-3-flash-preview-20251217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1744
moderation_latency
(null)
generation_time
37644
tokens_prompt
77
tokens_completion
2372
native_tokens_prompt
67
native_tokens_completion
8421
native_tokens_completion_images
0
native_tokens_reasoning
8189
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
0.0252965
router
(null)
provider_responses
0
endpoint_id
"6e82f652-2693-4b60-bbe0-7362d6e345f0"
is_byok
false
latency
1744
model_permaslug
"google/gemini-3-flash-preview-20251217"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771981037-ZHXi2ddcRUHxfnwluZtF"
upstream_id
(null)
total_cost
0.0252965
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
99.72%
Dialogue to Total Word Ratio
Ratio: 7.69%, Deviation: 2.31%
neededClean
false
wordsTotal
195
wordsDialogue
15
98.6722%