NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-19-01KS0TSXPMPNQZPJBB6RCD7GWN
Run Details
Model:
Gemini 3.5 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
31.3s
Cost:
$0.074117
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 fake mustache. Bill squeezed his burly frame into a green, inflatable dinosaur suit. They crouched tensely behind a sticky candy machine, eyeing the chaotic afternoon birthday party. "Is the backyard distraction ready?" asked Molly, checking her golden pocket watch. "I stuffed the pinata with fifty angry hornets," confessed Bill proudly. "That is horrific, Bill. We want precious toys, not a swarm of angry toddlers and federal lawsuits," hissed Molly, rubbing her temples. "Fine, I will use the giant bubble machine instead," sighed Bill, nervously adjusting his plastic tail. "Perfect. Once balloons and bubbles fill the yard, we will breach the unlocked glass sliding doors." Molly unrolled a crayon drawn map showing the playroom interior layout. "Where is the main treasure pile located?" asked Bill, squinting through his foggy visor goggles. "The glorious gift table stands right next to the chocolate cake," Molly pointed a gloved finger at the diagram. "I must grab the giant Lego starship," declared Bill, clutching a massive burlap sack. "Do not forget the wrapped boxes. If we play this right, we will be incredibly rich in orange juice boxes," whispered Molly, flashing a devious, toothy grin before they bolted forward toward the lawn.
created_at
"2026-05-19T19:18:34.969Z"
5/19/2026, 7:18:34 PM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1459
moderation_latency
(null)
generation_time
31202
tokens_prompt
77
tokens_completion
2468
native_tokens_prompt
67
native_tokens_completion
8224
native_tokens_completion_images
0
native_tokens_reasoning
7956
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
0.0741165
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"i7cMaobdBoG9sOIPkcaGkAs"
is_byok
false
latency
1459
model_permaslug
"google/gemini-3.5-flash-20260519"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer
(null)
request_id
"req-1779218314-Feqpx26OItXyyEHW0sE7"
session_id
(null)
api_type
"completions"
id
"gen-1779218314-xGbXOO85L2uSTRmC59I4"
upstream_id
"i7cMaobdBoG9sOIPkcaGkAs"
total_cost
0.0741165
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
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%