NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-19-01KS0TQ3SXT85PPPHXTDQTQDEK
Run Details
Model:
Gemini 3.5 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
1m 24s
Cost:
$0.209396
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 500 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 spread the blueprint across the hood of their rusty van. It was a detailed crayon drawing of a backyard. She tapped a red circle indicating the bouncy castle. Bill squinted at the paper while chewing on a cold french fry. He looked highly skeptical. "Explain this again, Molly. Why target a kid party? I thought we were art thieves." Molly rolled her eyes and slapped her hand against the dented metal hood, rattling loose bolts. "Art is subjective, Bill. What is not subjective? The value of thirty toy sets and two new tablets. The birthday boy is heir to a cookie empire. This haul is legendary. We just need to secure the goods and slip out." Bill scratched his beard, looking at the tactical crayon drawing. He pointed to a stick figure drawn near the patio. "And who is this? The primary security threat?" Molly adjusted her thick glasses, peering closer at her illustration. "That is Sparkles the Clown. He is a wildcard. Reports suggest he has rage issues. If he spots us, we deploy the smoke bombs." Bill sighed deeply, leaning back against the worn passenger seat. His fingers drummed a nervous rhythm against his dirty leather boots. "I do not want to fight a clown, Molly. It is bad luck. What about the kids? They are like sticky landmines. They run around without any plan." Molly pulled two oversized velvet sacks from a dusty duffel bag, tossing the heavier one onto his lap. "That is why we have costumes, you idiot. We are not going in as ourselves. We are the entertainment." Bill unzipped his sack, his jaw dropping as he pulled out a pink spandex unitard and a foam squirrel head. "Please tell me I am not the squirrel. Squirrels are twitchy. I do not have legs for this spandex." Molly smirked, pulling out her own costume, which was a puffy yellow duck suit. "You are Nutty the Squirrel, and I am Sir Quacks. The kids will be hypnotized. While they are distracted by our dance, we bag the presents and head for safety." Bill held the giant foam head up, staring somberly into its dead, completely unblinking cartoon eyes. "What if they want us to actually dance?" Molly grabbed her walkie talkie from the dashboard, checking the green battery light. "Then we jazz hand our way to financial freedom. Do you have the juice?" Bill reached into his pocket and produced a small plastic bottle, shaking it very gloomily. "Yes, but I still think that spiked juice is highly unprofessional." Molly snatched the bottle from him, quickly placing it into her yellow duck suit pocket. "It is melatonin, Bill. It will make them sleepy. Think of it as tactical naptime." He shook his head in absolute defeat, slowly pulling the giant squirrel head over his skull. "Let us get this over with before I lose all my dignity." Molly smiled brightly, finally zipping up her bright yellow duck suit. "That is the old, beautiful spirit."
created_at
"2026-05-19T19:17:02.914Z"
5/19/2026, 7:17:02 PM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1546
moderation_latency
(null)
generation_time
84179
tokens_prompt
77
tokens_completion
5318
native_tokens_prompt
67
native_tokens_completion
23255
native_tokens_completion_images
0
native_tokens_reasoning
22601
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
0.2093955
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"L7cMaoWZBMKf1MkPvtTOwA0"
is_byok
false
latency
1546
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-1779218222-9j71AfPgje2WSLOVJXOl"
session_id
(null)
api_type
"completions"
id
"gen-1779218222-zmnuE4lYbsML4ur3rKO3"
upstream_id
"L7cMaoWZBMKf1MkPvtTOwA0"
total_cost
0.2093955
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
500
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
250
100.0000%