NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8ZHJ63JPDB0YEKN2HE0PSQ
Run Details
Model:
Gemini 3.1 Flash Lite (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.0s
Cost:
$0.000401
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.0824%
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 her neon foam party hat, the elastic digging sharply into her scalp. Beside her, Bill wrestled with a bag of glittery confetti, his massive hands looking absurdly large against the delicate pastel wrapping paper of the decoy gift. They crouched behind a gargantuan, deflating birthday bounce castle that smelled faintly of sweaty socks and desperation. Outside, the cacophony of thirty screaming toddlers high on sugar signaled the prime extraction window. Molly squinted through the mesh window of the gift room, counting the pile of boxes labeled for the birthday boy. Her plan relied entirely on a synchronized distraction involving a rented clown and a very poorly secured cake stand. Bill wiped sweat from his brow, leaving a streak of cake frosting across his forehead. He checked his plastic digital watch, which was currently blinking a rhythmic strobe of red lights. The plan was chaotic, expensive, and deeply embarrassing for two career criminals. Molly nudged him with a sharp elbow, signaling the start of the final phase. Are you ready for this? Bill nodded grimly, gripping his duffel bag tight. For gold, maybe. For these plastic action figures, I feel pure shame. Molly sighed, ignoring his moral crisis, and kicked the castle door open.
created_at
"2026-05-10T12:59:37.547Z"
5/10/2026, 12:59:37 PM
model
"google/gemini-3.1-flash-lite-20260507"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
489
moderation_latency
(null)
generation_time
1879
tokens_prompt
77
tokens_completion
321
native_tokens_prompt
67
native_tokens_completion
256
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
0.00040075
router
(null)
provider_responses
0
endpoint_id
"237af107-d2e9-46c7-b146-c74d75980dee"
id
"OYEAav7aLYCsqtsP76-jEQ"
is_byok
false
latency
489
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-1778417977-IdLaBTk4utWv0vTQ5sp6"
session_id
(null)
api_type
"completions"
id
"gen-1778417977-apdgEy3lGkGNe4o23BiO"
upstream_id
"OYEAav7aLYCsqtsP76-jEQ"
total_cost
0.00040075
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
205
wordsDialogue
0
68.0824%