NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ95RK3B7KX5R89FX1HT1PQJ
Run Details
Model:
Gemini 2.5 Flash Lite (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.0s
Cost:
$0.000887
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
92.97%
Dialogue to Total Word Ratio
(details)
96.4849%
Overall
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
Molly squinted through the slightly grimy window of their ‘borrowed’ van, a child’s rendition of ‘Happy Birthday’ warbling faintly from down the street. Bill fidgeted in the driver’s seat, polishing a slightly bent crowbar with a greasy rag. Colourful balloons bobbed erratically against the setting sun behind the suburban house next door, each one a tiny beacon of their objective. Inside, tiny shrieks of delight, punctuated by the crinkle of wrapping paper, painted a vivid picture. The prize: a veritable mountain of birthday loot, just waiting to be liberated from the clutches of untamed toddler greed. Molly adjusted her balaclava, which smelled vaguely of old cheese and desperation. "Operation: Present Pandemonium is a go?" Bill whispered, checking his watch. Molly grinned. "Affirmative. Let's get these surplus joys to a more appreciative market." This was less about actual monetary value and more about the sheer principle of reappropriating joy that was, in their expert opinion, being squandered on sugar-fueled rugrats who’d forget it all by Tuesday. Their plan involved a swift, silent entrance during the cake cutting, a grab-and-dash of the largest, most ostentatiously wrapped items, and a quick getaway before the inevitable sugar crash led to a full-blown tantrum meltdown.
created_at
"2026-02-25T01:14:08.371Z"
2/25/2026, 1:14:08 AM
model
"google/gemini-2.5-flash-lite"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1119
moderation_latency
(null)
generation_time
6944
tokens_prompt
77
tokens_completion
1156
native_tokens_prompt
67
native_tokens_completion
2201
native_tokens_completion_images
0
native_tokens_reasoning
1926
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
0.0008871
router
(null)
provider_responses
0
endpoint_id
"ce839073-aa24-4f29-8358-15b319bd05ec"
is_byok
false
latency
1119
model_permaslug
"google/gemini-2.5-flash-lite"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771982048-sCAoAYE0omMpONH8YmKy"
upstream_id
(null)
total_cost
0.0008871
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
92.97%
Dialogue to Total Word Ratio
Ratio: 15.20%, Deviation: 5.20%
neededClean
false
wordsTotal
204
wordsDialogue
31
96.4849%