Model

Gemini 2.5 Pro

Test

Dialogue tags

Scenario

Write 200 words with 90% dialogue

Run ID

2025-11-18-01KACP6K6G44A1QGJH9PQQ75HP

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
"Operation Birthday Bandit is a go. The target is seven." "Right. Got the blueprints." Bill unfolded a party invitation. "It shows a bouncy castle near the primary entry point." "Ignore the bouncy castle, Bill." "But it's a tactical asset. And bouncy." "We are not using the bouncy castle for our exfiltration. What's your disguise?" "A magician," he declared. "Misdirection. 'Behold, I shall make the presents… vanish!'" "You can't do magic." "Details. What's your cover?" "I'm the face painter." "Boring. You should be the pony. I'll be the front end!" "You're on balloon animal duty," she snapped. "That's our way in. Can you make a decent sword?" "I can make a convincing worm." "Perfect. Distract them with worms. We strike during the cake-cutting sugar rush. Now, synchronize your watch with my party horn." "Does it play a little tune?" "It plays 'Get the loot, you idiot.'"
created_at"2025-11-18T23:53:51.454851+00:00" Tuesday, November 18th, 2025 at 11:53:51 PM GMT+00:00
model"google/gemini-2.5-pro" 
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2156
moderation_latency(null)
generation_time17302
tokens_prompt68
tokens_completion781
native_tokens_prompt67
native_tokens_completion2119
native_tokens_completion_images0
native_tokens_reasoning1886
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" 
usage0.02127375
api_type"completions" 
id"gen-1763510013-qh3pkr94B9py5fdxB3sX" 
upstream_id(null)
total_cost0.02127375
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
words146
97.8588% Dialogue to Total Word Ratio
Ratio: 93.84%, Deviation: 3.84%
neededCleanfalse
wordsTotal146
wordsDialogue137
48.9294%