NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Pro
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-11-18-01KACP40PYE0VVQ1V9P85D1X4M
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
"What's our window?" "The magician. Ten-thirty. He saws a dad in half, creates mass distraction." "Perfect. I go for the gift table. You're on lookout." "What am I looking out for?" "Hostiles. Parents with iPhones. Anyone under four feet tall who looks suspicious." "So, all of them?" "Precisely. And Bill?" "Yeah?" "Stay away from the piƱata. We don't have a contingency for a sugar-crazed mob." "But what if it's full of good candy? Not that cheap stuff." "The prize is the pile of boxed robotics and video games, not a handful of Laffy Taffy." "Right. Eyes on the prize. Can I at least get a balloon animal on the way out?" "Bill." "Just a sword. A quick one." "We are extracting the assets and leaving. No balloon swords." "Fine," he sighed. "But if I see the face-painting station, I can't make any promises." "Just be ready on my signal." "Promise you'll save me some cake?"
created_at
"2025-11-18T23:52:31.689834+00:00"
Tuesday, November 18th, 2025 at 11:52:31 PM GMT+00:00
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2745
moderation_latency
(null)
generation_time
22319
tokens_prompt
68
tokens_completion
1060
native_tokens_prompt
67
native_tokens_completion
2793
native_tokens_completion_images
0
native_tokens_reasoning
2548
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
0.02801375
api_type
"completions"
id
"gen-1763509928-9uogwqe5OCHxGWCd79cI"
upstream_id
(null)
total_cost
0.02801375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
158
55.8806%
Dialogue to Total Word Ratio
Ratio: 98.73%, Deviation: 8.73%
neededClean
false
wordsTotal
158
wordsDialogue
156
27.9403%