NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-11-18-01KACP8ZABDBWKY9RXGQ3MG9XY
Run Details
Model:
Gemini 2.5 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.4s
Cost:
$0.000790
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
21.4393%
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
"Right, so the bouncy castle is actually a distraction." "Obviously, Bill. No self-respecting thief gets caught by an inflatable dragon." "True. But it’s big. And loud. We need big and loud." "We need small and quiet. Like me, slipping past Mrs. Henderson’s prize-winning petunias." "No, wait. The petunias are motion-activated. She told me." "She told you? Why were you chatting with the target, Bill?" "Friendly reconnaissance. Anyway, the plan. You distract the parents with… interpretive dance?" "Interpretive dance? Bill, I’m a professional, not a circus act. I’m retrieving the goods." "Retrieving the goods implies you’re getting them from somewhere. Where are they?" "Underneath the giant 'Happy Birthday Bethany' banner, next to the clown with questionable hygiene." "Ah, the clown. Good, he's a known quantity. Always late, always sticky." "You’re the lookout, right? From the treehouse." "Treehouse? Molly, that thing looks like it's held together with hope and glitter glue. I'm ground support." "Fine. Ground support it is. Just don't let any nine-year-olds see you." "Nine-year-olds are the most dangerous, Molly. That’s why we need that bouncy castle."
created_at
"2025-11-18T23:54:53.779369+00:00"
11/18/2025, 11:54:53 PM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
413
moderation_latency
(null)
generation_time
2382
tokens_prompt
68
tokens_completion
277
native_tokens_prompt
67
native_tokens_completion
308
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
usage
0.0007901
api_type
"completions"
id
"gen-1763510091-1JedpnNuMGR7WM3Bzemc"
upstream_id
(null)
total_cost
0.0007901
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
6.09%
Matches word count
n/a
neededClean
false
words
177
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
184
wordsDialogue
184
21.4393%