NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAAS4JPKGP0W8HTCV9TQTA
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6.2s
Cost:
$0.000037
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.01%
Matches word count
(details)
0.03%
Dialogue to Total Word Ratio
(details)
0.0202%
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
Rain lashed against the window of the laundromat, mirroring the frantic energy swirling in Molly’s brain. Bill, meanwhile, was meticulously folding a pair of miniature clown socks. "Right," Molly began, pacing. "Operation Sugar Rush. Are you *sure* about this, Bill? It’s presents. For children. We're stealing presents from children." Bill glanced up, a sock dangling from his fingers. "Look, Molly. Think of it as…resource redistribution. These kids probably have too many. And we, demonstrably, have too few." "That's not how it works!" Molly protested. "What’s the security like? I'm picturing bouncy castles patrolled by ex-military parents.” “Relax. The invite says face painting and a petting zoo. Security’s probably a slightly overwhelmed teenager with a nametag." Bill punctuated the sentence by neatly creasing the sock. "We go in during the piñata, grab as much as we can, and vanish. Simple." "Simple? We’re stealing from toddlers, Bill! And what about the petting zoo? What if a llama sees us?" Molly wrung her hands. Bill shrugged. “Llamas are easily distracted by glitter.”
created_at
"2026-02-20T20:02:19.931Z"
2/20/2026, 8:02:19 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
167
moderation_latency
(null)
generation_time
6056
tokens_prompt
93
tokens_completion
292
native_tokens_prompt
75
native_tokens_completion
262
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
0.00003706
router
(null)
provider_responses
0
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-RkqKye2sHgxdIDP14upOuWJD"
is_byok
false
latency
47
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771617739-wjs8wMNFhKMpBIiuGzVT"
upstream_id
"chatcmpl-RkqKye2sHgxdIDP14upOuWJD"
total_cost
0.00003706
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.01%
Matches word count
n/a
neededClean
false
words
169
0.03%
Dialogue to Total Word Ratio
Ratio: 66.86%, Deviation: 16.86%
neededClean
false
wordsTotal
169
wordsDialogue
113
0.0202%