NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Flash Lite
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2025-11-18-01KACP4Y7EYK8PP13E7FT5Q5DF
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
The bouncy castle, a garish pink monstrosity, wobbled precariously. Molly, perched on the garden fence, adjusted her oversized sunglasses. “Right, the mission parameters are clear. Infiltration via the confetti cannon’s detonation. Distraction is paramount. Anyone see the cake?” Bill, crammed behind a suspiciously lumpy gnome, grunted. “Focus, Moll. Presents. That’s the treasure trove. Tiny hands, big greed. It’s a goldmine of wrapping paper and disappointment.” He poked his head out. “Are we sure about this? Last time we tried a kindergarten, the juice box incident was… sticky.” “That was a tactical error of judgement on your part,” Molly retorted, a glint in her eye. “This is a professional operation. Observe the target. Aunt Susan’s got good taste. Those boxes are substantial. We strike when the singing reaches its crescendo. You handle the egress, I’ll manage the haul.” “So, the plan is basically… steal from babies?” Bill sighed, a faint whiff of desperation clinging to him. “Lovely.”
created_at
"2025-11-18T23:52:40.86703+00:00"
Tuesday, November 18th, 2025 at 11:52:40 PM GMT+00:00
model
"google/gemini-2.5-flash-lite"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
199
moderation_latency
(null)
generation_time
1097
tokens_prompt
68
tokens_completion
233
native_tokens_prompt
67
native_tokens_completion
228
native_tokens_completion_images
0
native_tokens_reasoning
0
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
0.0000979
api_type
"completions"
id
"gen-1763509958-ZwJgSKyZZl5TcwxsGID4"
upstream_id
(null)
total_cost
0.0000979
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
156
0.0000%
Dialogue to Total Word Ratio
Ratio: 68.59%, Deviation: 58.59%
neededClean
false
wordsTotal
156
wordsDialogue
107
0.0000%