NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ94KS1TC9VG0C14C2W3D4VE
Run Details
Model:
Gemini 3 Flash (Preview, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
41.9s
Cost:
$0.025468
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.63%
Dialogue to Total Word Ratio
(details)
99.8127%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 adjusted her neon tutu, squinting through the suburban hedge at the target. Bill struggled with his oversized clown shoes, tripping over a discarded hula hoop. He wiped sweat from his face with a rubber nose. Molly checked her tactical watch, which featured a smiling cartoon sun. The backyard erupted with high-pitched screams and the chaotic melody of a cheap kazoo. Bill clutched a reinforced burlap sack labeled ‘loot’ in sparkly pink disco glitter. They crouched behind a rainbow-colored slide, waiting for the sugar rush to subside. Molly signaled with a gloved hand, her expression grim despite plastic fairy wings. "This is the big one, Bill. The bouncy castle is our Trojan Horse." "I think I’m too old for spandex, Molly. It pinches my soul." "Focus! The juice boxes are spiked with chamomile. We move at nap time." "Is the dog a problem? That golden retriever looks suspiciously vigilant." "That’s a toddler. Use glitter bombs if things get hairy." "And the cake? Can we secure Funfetti? It’s vital for morale." "Prioritize Lego sets first. We aren't here for snacks." "But it has sprinkles, Molly. Beautiful, tiny sprinkles." "Steal the Lego, or I leave you." "I'm keeping the balloon animal regardless."
created_at
"2026-02-25T00:54:02.047Z"
2/25/2026, 12:54:02 AM
model
"google/gemini-3-flash-preview-20251217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1832
moderation_latency
(null)
generation_time
41849
tokens_prompt
77
tokens_completion
2423
native_tokens_prompt
67
native_tokens_completion
8478
native_tokens_completion_images
0
native_tokens_reasoning
8191
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
0.0254675
router
(null)
provider_responses
0
endpoint_id
"6e82f652-2693-4b60-bbe0-7362d6e345f0"
is_byok
false
latency
1832
model_permaslug
"google/gemini-3-flash-preview-20251217"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771980842-unWZYbBuDrSGKhPCnvwZ"
upstream_id
(null)
total_cost
0.0254675
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
99.63%
Dialogue to Total Word Ratio
Ratio: 52.48%, Deviation: 2.48%
neededClean
false
wordsTotal
202
wordsDialogue
106
99.8127%