NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7GX9KCYDZDXTYNWMZSXBS
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.2s
Cost:
$0.000039
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
3.0453%
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 behemoth in the suburban garden. Molly adjusted her oversized sunglasses. “Right, Operation Sugar Rush is a go. You got the diversion?” Bill fumbled with a small, battery-powered robot dog. “Sparky here’s programmed to chase squirrels. Should draw most of the five-year-olds away from the prize pile. What about you?” “I’m the distraction extraordinaire. I’ll be ‘Aunt Mildred,’ overly enthusiastic about face painting. Glitter bombardment, guaranteed. They won’t suspect a thing.” Molly grinned, a flash of gold tooth. “Glitter? Really, Molly? Seriously?” Bill sighed, fiddling with Sparky’s antennae. “Hey, it’s festive! Besides, the presents are all wrapped in that cheap paper. Easy peel. You get the big train set, I’m taking the pony. We split it sixty-forty, my charm is harder work.” Bill gave her a withering look. “Sixty-forty? I’m risking being chased by a swarm of sugar-fueled toddlers!” “Think of the profits, Bill. Think of early retirement! Now, initiate Sparky. And try to look less like you're about to rob a children’s party, please.”
created_at
"2026-02-20T19:13:15.418Z"
2/20/2026, 7:13:15 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
352
moderation_latency
(null)
generation_time
6594
tokens_prompt
93
tokens_completion
306
native_tokens_prompt
75
native_tokens_completion
277
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
0.00003901
router
(null)
provider_responses
0
endpoint_id
"5aef2a85-3d1c-4659-a522-98bbb5272c6a"
is_byok
false
latency
32
model_permaslug
"google/gemma-3-12b-it"
provider_name
"Crusoe"
status
429
1
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-RTqfXMBBG13Q4XsGMSVaQ7eV"
is_byok
false
latency
37
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771614795-AblHBMat0ai9XcpgKJLI"
upstream_id
"chatcmpl-RTqfXMBBG13Q4XsGMSVaQ7eV"
total_cost
0.00003901
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
6.09%
Matches word count
n/a
neededClean
false
words
177
0.00%
Dialogue to Total Word Ratio
Ratio: 74.01%, Deviation: 24.01%
neededClean
false
wordsTotal
177
wordsDialogue
131
3.0453%