NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ95SFA8TCJJMRJZ7G5RE6HK
Run Details
Model:
Gemini 3 Flash (Preview, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
42.7s
Cost:
$0.025555
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
43.1902%
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
Molly checked her plastic watch and adjusted her cardboard crown. Everything hinges on the cake, Bill. The cake is a lie, Molly. Don't quote internet memes at me. When the candles go out, we strike. Are you sure about the clown? He has shifty eyes and a squeaky nose. The clown is a mere distraction. The real mark is that pile of glittery boxes near the organic juice boxes. It’s a lot of pink, Molly. That’s why we’re wearing the local camouflage. We’re wearing party hats and polyester capes. It's urban blending, Bill. Now, did you secure our transport? The tricycle is stashed behind the hydrangeas. It’s got a bell and everything. Excellent. Once the sugar rush hits, the perimeter will be compromised by sheer chaos. What about the birthday boy? He’s six. Lull him with the promise of a balloon animal, then vanish into the shadows. You’re cold, Molly. Stone cold. I’m a professional. Are the juice boxes spiked? With extra pulp. They won’t know what hit them. Good. At 1400 hours, we infiltrate the bouncy castle. Do I have to take my shoes off? Security protocols, Bill. No shoes on the vinyl. Right. For the Legos. For the Legos. Bill nodded solemnly and slowly tightened his yellow polyester cape.
created_at
"2026-02-25T01:14:37.263Z"
2/25/2026, 1:14:37 AM
model
"google/gemini-3-flash-preview-20251217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1706
moderation_latency
(null)
generation_time
42638
tokens_prompt
77
tokens_completion
2634
native_tokens_prompt
67
native_tokens_completion
8507
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
0.0255545
router
(null)
provider_responses
0
endpoint_id
"6e82f652-2693-4b60-bbe0-7362d6e345f0"
is_byok
false
latency
1706
model_permaslug
"google/gemini-3-flash-preview-20251217"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771982077-fUUEJgSndRS3kkGqucqz"
upstream_id
(null)
total_cost
0.0255545
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
211
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
211
wordsDialogue
0
43.1902%