NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ952SPW80WVDFPGB4C9N50C
Run Details
Model:
Gemini 3 Flash (Preview, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.0s
Cost:
$0.005361
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.6885%
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
Check the schematics again, Bill. The bouncy castle provides a three-minute blind spot. Molly, it's a giant neon dragon, not a mountain range. Exactly. The guards won’t see us through the inflatable wings. The guards are kindergarteners in capes, and they’re vibrating from a sugar high. Which makes them unstable. We breach the gift table at precisely 14:00 hours, right as the double-fudge cake hits the table. Is the clown an issue? Bill asked, adjusting his sunglasses. Giggles? He’s the diversion. Once the balloon animals start, the perimeter dissolves. If he switches to card tricks, the crowd thins and we’re cooked. I’m not wearing the tactical tutu again. It’s suburban camouflage! You blend in with the garden ornaments. It itches, Molly. What’s the expected haul? Lego sets, drones, and maybe a high-end tablet if Timmy’s grandma is as loaded as the intel suggests. What if a toddler latches onto my leg? You shake them off and keep moving. No distractions. It’s a scale-model backyard, Molly. We're robbing a seven-year-old. It’s the score of century, Molly whispered, pointing at the crayon-drawn map. Once the piñata explodes, it’s go-time. I just hope there’s a Nintendo in those boxes. Stay sharp, or you’re getting juice boxes for dinner.
created_at
"2026-02-25T01:02:14.242Z"
2/25/2026, 1:02:14 AM
model
"google/gemini-3-flash-preview-20251217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1829
moderation_latency
(null)
generation_time
10917
tokens_prompt
77
tokens_completion
974
native_tokens_prompt
67
native_tokens_completion
1776
native_tokens_completion_images
0
native_tokens_reasoning
1446
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
0.0053615
router
(null)
provider_responses
0
endpoint_id
"6e82f652-2693-4b60-bbe0-7362d6e345f0"
is_byok
false
latency
1825
model_permaslug
"google/gemini-3-flash-preview-20251217"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771981334-higAq8FnzDrjNPPEtYws"
upstream_id
(null)
total_cost
0.0053615
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
213
wordsDialogue
0
49.6885%