NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYB3CJ945VV4EBTD2X1AFVW
Run Details
Model:
Gemma 3 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.6s
Cost:
$0.000112
Provider:
Phala
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 bouncy castle’s a no-go. Too public.” “But think of the cover, Molly! No one suspects a pair of grannies attempting a bouncy castle.” “Bill, we’re forty-two and thirty-eight, not eighty-two and seventy-eight. And you’d get stuck.” “A small price to pay for a haul of remote control cars and gaming consoles! What about through the kitchen?” “Too many parents. Always lurking with lukewarm buffet food. No. We need subtlety.” “Subtlety? We’re stealing presents from a six-year-old, Molly. There’s no subtlety involved.” “There is if we want to avoid jail time! Okay, ventilation shaft. Small, yes, but efficient.” “Ventilation shaft? You’re kidding. Last time you suggested a ventilation shaft we ended up covered in pigeon feathers.” “That was a *different* ventilation shaft, Bill! This one’s… shinier. Probably. Look, it’s either that or disguise ourselves as a giant inflatable dinosaur.” “Honestly, the dinosaur is starting to sound appealing.” “Focus, Bill. Presents. Shiny, beautifully wrapped presents.”
created_at
"2026-02-20T20:15:46.259Z"
2/20/2026, 8:15:46 PM
model
"google/gemma-3-27b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
428
moderation_latency
(null)
generation_time
6423
tokens_prompt
93
tokens_completion
301
native_tokens_prompt
75
native_tokens_completion
260
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
0.00011225
router
(null)
provider_responses
0
endpoint_id
"cf530f36-7cb8-4eb9-8953-880eef952af3"
is_byok
false
latency
5093
model_permaslug
"google/gemma-3-27b-it"
provider_name
"Novita"
status
(null)
1
endpoint_id
"1d5251f0-02fd-484b-bb6c-d346277c8a0d"
id
"cmpl-7a237cfc35a74534b5ed5600865bf3d8"
is_byok
false
latency
347
model_permaslug
"google/gemma-3-27b-it"
provider_name
"Phala"
status
200
api_type
"completions"
id
"gen-1771618546-2xNEjHvyftq4bvUO2dyX"
upstream_id
"cmpl-7a237cfc35a74534b5ed5600865bf3d8"
total_cost
0.00011225
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Phala"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
162
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
162
wordsDialogue
162
18.3940%