NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR910T053ZZ1GDBM5S015TCF
Run Details
Model:
Gemini 3.1 Flash Lite
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.1s
Cost:
$0.000398
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
67.2078%
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 crouched behind the decorative topiary, her eyes fixed on the suburban sprawl of a backyard transformed into a neon nightmare of inflatable castles and screaming toddlers. The air hung thick with the cloying, sugary scent of cheap frosting and desperation. Beside her, Bill adjusted his neon clown wig, his movements jerky and filled with the nervous energy of a man who realized too late that donning oversized polka-dotted shoes made tactical infiltration exceptionally difficult. They were here for the loot. According to their intel, the birthday boy had received an original 1984 prototype action figure, a collector's item worth enough to fund their retirement in a country without extradition treaties. Bill nudged her shoulder, his nose squeaking against his cheek. Do you think they suspect? Molly rolled her eyes, checking the structural integrity of the fence. They are five years old, Bill. They suspect the punch is laced with beet juice. Behind the folding table, a mountain of glitter-covered boxes sat unguarded. The clowns were currently occupied with a balloon animal massacre. Molly signaled the countdown. We strike when the cake hits the table. Bill nodded, licking his fingers in anticipation. Let us bag the haul. They surged forward as the sugar-fueled chaos reached its apex.
created_at
"2026-05-10T13:25:25.644Z"
5/10/2026, 1:25:25 PM
model
"google/gemini-3.1-flash-lite-20260507"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
509
moderation_latency
(null)
generation_time
2016
tokens_prompt
77
tokens_completion
327
native_tokens_prompt
67
native_tokens_completion
254
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
0.00039775
router
(null)
provider_responses
0
endpoint_id
"237af107-d2e9-46c7-b146-c74d75980dee"
id
"RYcAasDEM8mtz7IPz4DMuQY"
is_byok
false
latency
509
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-1778419525-FT29tL71Nk40KAhU21Dj"
session_id
(null)
api_type
"completions"
id
"gen-1778419525-74dk5mPCagU5HfaWcCtP"
upstream_id
"RYcAasDEM8mtz7IPz4DMuQY"
total_cost
0.00039775
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
207
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
210
wordsDialogue
0
67.2078%