NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY89JED01QERD3G75GQVXKM
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.9s
Cost:
$0.000037
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
4.10%
Dialogue to Total Word Ratio
(details)
28.0111%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 dominating the cul-de-sac. Streamers drooped forlornly from the surrounding houses, remnants of a birthday party already winding down. Bill, disguised in a truly unfortunate clown costume, tugged at his oversized bow tie. It felt itchy, and frankly, ridiculous. Molly, meanwhile, was meticulously aligning a laser grid around the prize table, a fortress of brightly wrapped boxes. A small child, clutching a half-eaten cupcake, stared at Bill with wide, unblinking eyes. “Right,” Molly muttered, adjusting a sensor. “Timing is everything. As soon as the magician pulls the rabbit – the distraction, you know – you sweep in. Grab the big stuff first. Lego, anything remotely valuable.” Bill just grimaced. The clown shoes were pinching. A rogue balloon bumped against his nose. This felt wrong. Incredibly, profoundly childish. It was supposed to be a simple snatch-and-grab. In and out. No fuss. “You sure about this?” he mumbled, barely audible. Molly didn’t look up. “Positive. Shiny things, Bill. Think of the resale value.” She tapped her tablet. A red light blinked. “Almost time.”
created_at
"2026-02-20T19:26:43.168Z"
2/20/2026, 7:26:43 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
385
moderation_latency
(null)
generation_time
5780
tokens_prompt
93
tokens_completion
302
native_tokens_prompt
75
native_tokens_completion
261
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
0.00003693
router
(null)
provider_responses
0
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-RSCQTmWoxnOsYl9l4Ut4sTTq"
is_byok
false
latency
55
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771615603-3EclVgzSPLDDrSM6Aq47"
upstream_id
"chatcmpl-RSCQTmWoxnOsYl9l4Ut4sTTq"
total_cost
0.00003693
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
184
4.10%
Dialogue to Total Word Ratio
Ratio: 23.37%, Deviation: 13.37%
neededClean
false
wordsTotal
184
wordsDialogue
43
28.0111%