NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYB74SR21AEN4K8Q11MT0YV
Run Details
Model:
Gemma 3 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.6s
Cost:
$0.000110
Provider:
Phala
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
77.50%
Dialogue to Total Word Ratio
(details)
38.7508%
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
“Okay, so the inflatable castle is a no-go, right? Too conspicuous?” Molly asked, sketching rapidly in a tiny notebook. “Conspicuous? Molly, you’d blend in less dressed as a giraffe,” Bill retorted, polishing his glasses with a napkin. “We’re going for subtle. Think…concerned parents.” “Concerned parents who are systematically removing brightly wrapped gifts?” “They’re clearly overwhelmed. Overflowing generosity. We’re *helping* them.” Bill insisted, puffing out his chest. “Helping them to a lighter credit card bill, you mean.” “Details, details. The key is timing. During the magician. Everyone’s looking at rabbits and bad card tricks.” “What if the magician’s good?” Molly tapped her pen. “A really *good* magician? We can’t operate under a successful illusion.” “Then we improvise. Maybe heckle him? Distraction is key. And you, definitely no giraffe costumes.” “Fine. But I’m calling dibs on the remote control car.” “Naturally. Just don’t get caught singing ‘Happy Birthday’ to a pile of loot.”
created_at
"2026-02-20T20:17:49.379Z"
2/20/2026, 8:17:49 PM
model
"google/gemma-3-27b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
352
moderation_latency
(null)
generation_time
6487
tokens_prompt
93
tokens_completion
301
native_tokens_prompt
75
native_tokens_completion
254
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
0.00010985
router
(null)
provider_responses
0
endpoint_id
"1d5251f0-02fd-484b-bb6c-d346277c8a0d"
id
"cmpl-a168f576bf8b42c1bdc930b999f339dd"
is_byok
false
latency
251
model_permaslug
"google/gemma-3-27b-it"
provider_name
"Phala"
status
200
api_type
"completions"
id
"gen-1771618669-tOkhGurt3WVDVkEI3gH3"
upstream_id
"cmpl-a168f576bf8b42c1bdc930b999f339dd"
total_cost
0.00010985
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
152
77.50%
Dialogue to Total Word Ratio
Ratio: 82.89%, Deviation: 7.11%
neededClean
false
wordsTotal
152
wordsDialogue
126
38.7508%