NC Bench
Overview
About
Tests
Models
Model
Gemini 3 Pro (Preview)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-11-19-01KACQVQ42642G65EQ8N8GRV6C
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
All right, look at the schematics, Molly whispered, tapping the paper. This is a drawing of a pony, Bill said. It is a tactical map, Bill! Now focus. We have a three-minute window between the pin-the-tail diversion and the cake cutting. What about the perimeter guards? The parents are heavy on the chardonnay. Low threat. The real danger is the hired muscle. The clown? The clown. If he starts making balloon animals, the crowd density increases effectively trapping us in the kill zone. I can take him, Bill said. I know his weakness. Which is? Seltzer water? No! We stick to the plan. You create a distraction near the chocolate fountain. I am not dipping my hand in that again. Do you want the haul or not? We are talking about a limited edition action figure and at least three gift cards of indeterminate value. Fine. But what if the target spots me? The birthday boy brings heat. You engage the protocol. I cry until they give me a juice box? Exactly. It confuses the enemy. Then we grab the loot bag and extract via the bouncy castle slide. The static electricity will fry our comms. It is a risk we have to take. This is the big one, Bill. The ultimate score. Stealing a four-year-old’s Lego set. Living the dream, baby. Masks on.
created_at
"2025-11-19T00:22:48.211025+00:00"
Wednesday, November 19th, 2025 at 12:22:48 AM GMT+00:00
model
"google/gemini-3-pro-preview-20251117"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2136
moderation_latency
(null)
generation_time
13991
tokens_prompt
68
tokens_completion
762
native_tokens_prompt
67
native_tokens_completion
1514
native_tokens_completion_images
0
native_tokens_reasoning
1207
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
0.018302
api_type
"completions"
id
"gen-1763511753-zqgrFUA3PutDzpgQo94S"
upstream_id
(null)
total_cost
0.018302
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0848%
Matches word count
n/a
neededClean
false
words
229
0.0000%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
229
wordsDialogue
0
0.0424%