NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7JNZ4SD2C96NEBZ5B0XDF
Run Details
Model:
Gemma 3 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6.3s
Cost:
$0.000121
Provider:
Phala
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
1.0058%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
The inflatable bouncy castle loomed, a garish pink and blue monstrosity. Molly squinted. “Honestly, Bill, a six-year-old’s birthday. Is this really the best we can do?” Bill, meticulously applying face paint, didn’t look up. “Don’t judge the target, Molly. Think of the haul. Brand new scooters, remote control cars, probably a small fortune in Lego. Untraceable, easy resale.” He finished a particularly enthusiastic stripe of purple across his cheek. “You look like a raccoon had a fight with a grape.” “It’s camouflage! They expect a clown, not two obviously suspicious adults.” He glanced around the manicured garden. “Timing is crucial. Precisely 3:17. That’s when little Timmy will be distracted by the pinata.” “And we waltz in, grab the gifts, and vanish? Sounds… undignified.” “Undignified pays the bills, Molly. And think of the irony. Stealing joy to *buy* joy. It’s practically philosophical. Now, where’s the oversized bag?” “Already in the van, along with the escape route mapped and the glitter cannon pre-loaded.” Bill grinned. “Excellent. Let’s go make a six-year-old very disappointed.”
created_at
"2026-02-20T19:14:13.105Z"
2/20/2026, 7:14:13 PM
model
"google/gemma-3-27b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
252
moderation_latency
(null)
generation_time
6164
tokens_prompt
93
tokens_completion
314
native_tokens_prompt
75
native_tokens_completion
283
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
0.00012145
router
(null)
provider_responses
0
endpoint_id
"1d5251f0-02fd-484b-bb6c-d346277c8a0d"
id
"cmpl-88b7fe4a697e4fb4be684c749f3fbd82"
is_byok
false
latency
241
model_permaslug
"google/gemma-3-27b-it"
provider_name
"Phala"
status
200
api_type
"completions"
id
"gen-1771614853-l5tTqVEjPEWmKw8NpKm8"
upstream_id
"cmpl-88b7fe4a697e4fb4be684c749f3fbd82"
total_cost
0.00012145
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Phala"
Evaluation details
Result
Evaluator
Details
Meta Data
2.01%
Matches word count
n/a
neededClean
false
words
175
0.00%
Dialogue to Total Word Ratio
Ratio: 77.14%, Deviation: 27.14%
neededClean
false
wordsTotal
175
wordsDialogue
135
1.0058%