NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ94N919DX4GA98C0KMMAN26
Run Details
Model:
Gemini 3 Flash (Preview, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
41.3s
Cost:
$0.025372
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3562%
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
Are you sure about the clown suit, Bill? It smells like failure and old greasepaint. It is the perfect disguise, Molly. No one questions a clown carrying a heavy sack. We are doing a heist. Targeted: The Madison birthday bash. Objective: Every Lego set and high-end tablet in that gazebo. I have the floor plan. The bounce house provides a blind spot. I slip in, grab the loot, and toss it over the fence. Molly squinted at the suburban lawn and adjusted her earpiece while checking the perimeter. And what if a toddler bites your ankle? They are feral when there is a sugar rush. I will distract them with balloon animals. I have been practicing. You made a latex sausage, Bill. That is not a dog. It is an abstract poodle! Focus. Once the cake comes out, that is our window. The parents will be distracted. I will be waiting by the hydrangeas. Do not get stuck in the ball pit. Bill adjusted his squeaky red nose. That was one single time! Those balls have no structural integrity. Are we synced? My watch says it is juice box time. Let us move, partner.
created_at
"2026-02-25T00:54:51.186Z"
2/25/2026, 12:54:51 AM
model
"google/gemini-3-flash-preview-20251217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1995
moderation_latency
(null)
generation_time
41246
tokens_prompt
77
tokens_completion
2770
native_tokens_prompt
67
native_tokens_completion
8446
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
0.0253715
router
(null)
provider_responses
0
endpoint_id
"6e82f652-2693-4b60-bbe0-7362d6e345f0"
is_byok
false
latency
1995
model_permaslug
"google/gemini-3-flash-preview-20251217"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771980891-B9PoPTPKBEuMdlh2thtQ"
upstream_id
(null)
total_cost
0.0253715
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
195
wordsDialogue
0
49.3562%