NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8Y4S1V2F8Z4Q977HEHC6W6
Run Details
Model:
Gemini 3.1 Flash Lite
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
33.8s
Cost:
$0.000381
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3935%
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 adjusted the oversized velvet bowtie that chafed against her neck, itching with the nervous energy of an undercover clown. Beside her, Bill wrestled with a bag of confetti that had already begun to leak, dusting his tactical turtleneck in festive glitter. They crouched behind a sprawling hydrangeas bush, peering through the living room window of the suburban fortress. Inside, a bouncy castle inflated like a giant, neon lung, threatening to consume the living room floor. Dozens of toddlers swarmed the centerpiece mountain of brightly wrapped boxes, their high-pitched squeals sounding like a gathering of caffeinated hyenas. Their mother, a woman who strictly enforced screen time, stood guard with a smartphone held like a shield. Molly checked her watch, the ticking heart of their operation. They had exactly three minutes before the cake reveal shifted the crowd toward the kitchen. Bill checked his lockpicks, his fingers moving with frantic, clumsy precision. Let us grab the haul and vanish, he whispered. Molly nodded, inhaling a deep breath of sterilized birthday air and bubble gum scent. We hit the presents hard, stay low, and never lock eyes with the toddler in the dragon onesie. They prepared to storm the bouncy castle.
created_at
"2026-05-10T12:35:10.018Z"
5/10/2026, 12:35:10 PM
model
"google/gemini-3.1-flash-lite-20260507"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
468
moderation_latency
(null)
generation_time
33722
tokens_prompt
77
tokens_completion
312
native_tokens_prompt
67
native_tokens_completion
243
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
0.00038125
router
(null)
provider_responses
0
endpoint_id
"237af107-d2e9-46c7-b146-c74d75980dee"
id
"fnsAaojhDeeHz7IPl5eaiQc"
is_byok
false
latency
468
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-1778416510-W5TiIWMRsGGDkOf5aIZC"
session_id
(null)
api_type
"completions"
id
"gen-1778416510-KJYMekwDTugsarH7ccMB"
upstream_id
"fnsAaojhDeeHz7IPl5eaiQc"
total_cost
0.00038125
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
199
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
200
wordsDialogue
0
68.3935%