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

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_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2745
moderation_latency(null)
generation_time22319
tokens_prompt68
tokens_completion1060
native_tokens_prompt67
native_tokens_completion2793
native_tokens_completion_images0
native_tokens_reasoning2548
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/" 
is_byokfalse
finish_reason"stop" 
native_finish_reason"STOP" 
usage0.02801375
api_type"completions" 
id"gen-1763509928-9uogwqe5OCHxGWCd79cI" 
upstream_id(null)
total_cost0.02801375
cache_discount(null)
upstream_inference_cost0
provider_name"Google AI Studio" 

Evaluation details

Result Evaluator Details Meta Data
0.0000% Matches word count n/a
neededCleanfalse
words158
55.8806% Dialogue to Total Word Ratio
Ratio: 98.73%, Deviation: 8.73%
neededCleanfalse
wordsTotal158
wordsDialogue156
27.9403%