NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-19-01KS0V408N63ENY1KAVJNGP86F
Run Details
Model:
Gemini 3.5 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.0s
Cost:
$0.030565
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
98.92%
Dialogue to Total Word Ratio
(details)
83.5104%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"So, we hit the bouncy castle at two?" Bill asked, adjusting his fake mustache. "No, Bill, the bounce house is our extraction zone," Molly whispered, tapping the map. "We strike during the cake." "But what about the clown? He looks shifty." "The clown is a sixteen-year-old named Kevin. He gets paid in cheap pizza and self-loathing. He is not a threat." "And the primary target?" "The pile of wrapped loot in the sunroom. It is a goldmine of Lego, laser tag vouchers, and hopefully a Nintendo Switch." "Do we use the smoke bombs?" "Absolutely no smoke bombs! It’s an eight-year-old's birthday, not a bank vault. We use the decoy." "The llama pinata?" "Exactly. You yell, 'Look, a loose pony!' and when the sugar-crazed children swarm the lawn, I slip inside and bag the goods." "What if they unleash the family golden retriever?" "I brought premium beef jerky. He'll turn on them in seconds," she smirked. "Brilliant. But Molly?" "Yes, Bill?" "If there’s an ice cream cake in the freezer, can we steal that too? It is really hot today." "Focus, Bill. We are highly trained professionals."
created_at
"2026-05-19T19:24:05.274Z"
5/19/2026, 7:24:05 PM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1592
moderation_latency
(null)
generation_time
13875
tokens_prompt
77
tokens_completion
1302
native_tokens_prompt
67
native_tokens_completion
3385
native_tokens_completion_images
0
native_tokens_reasoning
3091
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
0.0305655
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"1bgMauOxGZGkjrEPjL-AmQc"
is_byok
false
latency
1592
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-1779218645-5npfson7OAPYDtPb30fk"
session_id
(null)
api_type
"completions"
id
"gen-1779218645-iLXm7LVAhIXVoOcsW5A8"
upstream_id
"1bgMauOxGZGkjrEPjL-AmQc"
total_cost
0.0305655
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
186
98.92%
Dialogue to Total Word Ratio
Ratio: 93.23%, Deviation: 3.23%
neededClean
false
wordsTotal
192
wordsDialogue
179
83.5104%