NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR90BE18ZNHP6DNQF8WNTTHW
Run Details
Model:
Gemini 3.1 Flash Lite
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1.9s
Cost:
$0.000386
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3940%
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
The bouncy castle loomed like a neon pink fortress against the suburban dusk, vibrating with the frantic energy of thirty hyperactive seven-year-olds hooked on high-fructose corn syrup. Molly adjusted her tactical balaclava, which was unfortunately knitted in a cheerful bright yellow pattern because it was the only one left in the supply bin. Beside her, Bill crouched behind a suspiciously shaped plastic shrub, his grip tight on a velvet-lined duffel bag. We are targeting the loot table near the snack station, Molly whispered while checking her watch. The objective is to secure the primary haul before the piƱata distraction begins. Bill nodded solemnly, squinting through his night-vision goggles that were currently flickering with a low-battery warning. They moved in precise, practiced maneuvers, weaving through the chaotic sea of sprinting toddlers and discarded juice boxes. Every muffled giggle from the nearby slide sounded like a siren in the quiet air of the backyard. They maintained a low profile, blending into the pastel madness with the frantic elegance of professional burglars who had hit rock bottom. If we manage to swipe the giant robot, I am keeping it, Bill muttered. Molly rolled her eyes, already calculating the weight of the stuffed toys.
created_at
"2026-05-10T13:13:45.263Z"
5/10/2026, 1:13:45 PM
model
"google/gemini-3.1-flash-lite-20260507"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
510
moderation_latency
(null)
generation_time
1800
tokens_prompt
77
tokens_completion
319
native_tokens_prompt
67
native_tokens_completion
246
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
service_tier
"standard"
usage
0.00038575
router
(null)
provider_responses
0
endpoint_id
"237af107-d2e9-46c7-b146-c74d75980dee"
id
"iYQAaqWeHaOCmtkPx-OWgQY"
is_byok
false
latency
510
model_permaslug
"google/gemini-3.1-flash-lite-20260507"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778418825-gAKc35pNh4wBngs1Y8C6"
session_id
(null)
api_type
"completions"
id
"gen-1778418825-IwzA2YleOr2rOeCDSepn"
upstream_id
"iYQAaqWeHaOCmtkPx-OWgQY"
total_cost
0.00038575
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
206
wordsDialogue
0
68.3940%