NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8T0NJ3GN6BAS3419DYCNG
Run Details
Model:
Gemma 3 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.0s
Cost:
$0.000127
Provider:
Parasail
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
18.3940%
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 inflatable castles and…balloons. Honestly, Bill, a children’s party?” “Prime target, Molly, prime. Untapped potential. Everyone focuses on banks, museums. Nobody thinks of the presents.” “Because it’s…wrong? We’re stealing from *children*?” “Details, details. Think of the haul! Brand new gaming consoles, those little robotic dinosaurs, probably even a miniature pony if we’re lucky.” “A miniature pony? You’ve really done your research, haven't you?” “A man’s gotta dream! Look, the plan’s simple. You distract the magician with insistent questions about the rabbit. I go for the gift mountain.” “’Insistent questions’? I’m a master of disguise, not a six-year-old.” “Fine, ask him if the rabbit is ethically sourced. That’ll throw him. Just keep him occupied! They said there’s a bouncy castle guardian, though.” “A guardian? What, like a bouncer for bounce houses?” “Apparently. A particularly enthusiastic dad with a whistle. We’ll need a diversion for him too.” “Oh, this is getting complicated. Maybe we should just stick to banks.”
created_at
"2026-02-20T19:35:42.016Z"
2/20/2026, 7:35:42 PM
model
"google/gemma-3-27b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
495
moderation_latency
(null)
generation_time
8923
tokens_prompt
93
tokens_completion
313
native_tokens_prompt
75
native_tokens_completion
268
native_tokens_completion_images
(null)
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
0.0001266
router
(null)
provider_responses
0
endpoint_id
"2f608ade-87b1-46ed-8ae7-2714dddf2abb"
id
"cmpl-c1f123b0d6674bcfa9793f2cae477870"
is_byok
false
latency
389
model_permaslug
"google/gemma-3-27b-it"
provider_name
"Parasail"
status
200
api_type
"completions"
id
"gen-1771616142-1gMwGhxZJNT7WKuXbNol"
upstream_id
"cmpl-c1f123b0d6674bcfa9793f2cae477870"
total_cost
0.0001266
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Parasail"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
160
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
160
wordsDialogue
160
18.3940%