NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-11-18-01KACPAFFRB31NJCGH80089HTV
Run Details
Model:
Gemini 2.5 Flash Lite
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1.5s
Cost:
$0.000113
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
99.18%
Dialogue to Total Word Ratio
(details)
75.5536%
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
"Alright, Bill," Molly whispered, peering through the fence. "Operation Sugar Plum is a go. See that bouncy castle? Utter chaos. Perfect cover." "Chaos," Bill echoed, adjusting his oversized novelty sunglasses. "My favorite kind of chaos before I pocket some plastic dinos. So, the plan?" "Simple. While Brenda's busy wrestling a toddler into a dinosaur costume – you know how she gets about thematic accuracy – we slip through the back door. You handle the wrapping paper mountain by the tree. I'll deploy the stealth bag into the Lego fort." "Lego fort? Brilliant! The small pieces will blend right in. But what if a kid sees us with the good stuff? Like, the *really* good stuff? The remote-control car?" "Relax. Their attention spans are shorter than a fly's life. A well-timed glitter bomb – strategically placed on the cake table – will create a diversion of epic proportions. Then we grab and dash before they even finish crying." "Glitter bomb. Molly, you're a genius. Just… try not to aim it at the buffet. I was rather looking forward to those mini quiches." "Priorities, Bill. Priorities. Presents first, pastry second."
created_at
"2025-11-18T23:55:42.638102+00:00"
11/18/2025, 11:55:42 PM
model
"google/gemini-2.5-flash-lite"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
302
moderation_latency
(null)
generation_time
1504
tokens_prompt
68
tokens_completion
253
native_tokens_prompt
67
native_tokens_completion
266
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
0.0001131
api_type
"completions"
id
"gen-1763510140-y4joV5doy6asTm9i31rO"
upstream_id
(null)
total_cost
0.0001131
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
184
99.18%
Dialogue to Total Word Ratio
Ratio: 93.01%, Deviation: 3.01%
neededClean
false
wordsTotal
186
wordsDialogue
173
75.5536%