NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR90S1MHB0QBWW9DYMT2KA5Y
Run Details
Model:
Gemini 3.1 Flash Lite
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.2s
Cost:
$0.000408
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
45.2419%
Overall
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
Molly tightened her shoelaces and peered through the hedge at the sea of bouncing castles. Are those clowns armed? Bill whispered. They are holding balloon animals, Bill. One of those animals is a poodle with a clearly sharpened snout. Look, the drop is at three o'clock near the juice box station. And the loot? Molly asked, adjusting her balaclava. Stacked behind the cake, gleaming like gold. Forty-two gifts. If we move during the musical chairs frenzy, we can clear the table in seconds. What if the birthday boy intercepts? I have a pocket full of glitter bombs. He will be blinded by sparkle and joy. That is diabolical. I know. Now, are you ready to snatch these Legos or keep standing here smelling like cheap cake frosting? I was born ready. On your mark? Mark. They leapt over the hedge, landing squarely in a pile of discarded wrapping paper. Target acquired, Molly hissed as a bouncy castle lurched toward them like an inflatable titan. Split up! Bill yelled. And if we get caught? Tell them we are the cousins. The ones nobody invited. Right. See you in the getaway minivan.
created_at
"2026-05-10T13:21:11.321Z"
5/10/2026, 1:21:11 PM
model
"google/gemini-3.1-flash-lite-20260507"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
603
moderation_latency
(null)
generation_time
2129
tokens_prompt
77
tokens_completion
303
native_tokens_prompt
67
native_tokens_completion
261
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
0.00040825
router
(null)
provider_responses
0
endpoint_id
"237af107-d2e9-46c7-b146-c74d75980dee"
id
"R4YAauuNH-XlqtsPv-6f0QE"
is_byok
false
latency
603
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-1778419271-AKPKtFJx8E2SazzCrRaW"
session_id
(null)
api_type
"completions"
id
"gen-1778419271-3x01XYYP8lH3XSy3Neec"
upstream_id
"R4YAauuNH-XlqtsPv-6f0QE"
total_cost
0.00040825
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
190
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
191
wordsDialogue
0
45.2419%