NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-20-01KS25VPCWH53SJ3F59PREK3TM
Run Details
Model:
Gemini 3.5 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.4s
Cost:
$0.002341
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
65.2188%
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
The afternoon sun beat down on the rusty getaway minivan, which smelled faintly of onion dip and desperation. Molly gestured aggressively at a meticulously drawn, crayon-colored map of the target backyard, her fingernails tapping against the cardboard. Bill sat in the driver’s seat, struggling to squeeze his enormous frame into a fluorescent yellow safety vest that clearly belonged to a much smaller volunteer crosswalk guard. He adjusted his papier-mache toddler mask, his eyes blinking nervously through the crudely cut eyeholes. The stakes were incredibly low, yet the tension in the vehicle was stifling. Underneath Molly’s seat lay eighteen decoy juice boxes and a stash of expensive noise-canceling headphones meant to withstand the shrieks of twenty caffeinated seven-year-olds. She checked her watch, her jaw clenched with professional intensity. Success depended entirely on their ability to blend in with the distracted parents during the chaotic climax of the pinata devastation. We strike when they cut the cake, Molly whispered. Bill adjusted his vest. Are we sure about the red tricycle? It’s vintage, Bill, Molly snapped, tapping the map. Focus. She slid the side door open, bracing herself for the impending wall of sound.
created_at
"2026-05-20T07:51:01.792Z"
5/20/2026, 7:51:01 AM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
733
moderation_latency
(null)
generation_time
2252
tokens_prompt
77
tokens_completion
320
native_tokens_prompt
67
native_tokens_completion
249
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
0.0023415
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"5WcNaozNOcyz1MkPuOfk2As"
is_byok
false
latency
733
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-1779263461-rSOvx2Dt2IooHdnpDwDH"
session_id
(null)
api_type
"completions"
id
"gen-1779263461-OROwwgbsSN565IW7Dcss"
upstream_id
"5WcNaozNOcyz1MkPuOfk2As"
total_cost
0.0023415
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
196
wordsDialogue
0
65.2188%