NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9Y7Y8D1W4MZRV7GTXHDWS
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.0s
Cost:
$0.000037
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
99.96%
Dialogue to Total Word Ratio
(details)
98.7946%
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 bouncy castle loomed, a garish inflatable sentinel guarding a treasure trove of disappointment – piles and piles of brightly wrapped presents. Molly squinted, adjusting her oversized sunglasses. Bill, perpetually damp from a mysterious source, was meticulously cataloging the sugar-fueled chaos through a pair of binoculars. Tiny humans shrieked, launching themselves at each other with a startling lack of grace. Streamers whipped in the breeze like distressed flags. "Right," Molly muttered, making a note on a napkin covered in doodles. “Operation Sugar Rush is a go.” Bill lowered the binoculars, a single bead of moisture tracing a path down his cheek. “Seems...sticky.” Molly ignored him, sketching a route through the inflatable jungle. She envisioned a delicate maneuver, a graceful sidestep past a particularly enthusiastic child wielding a balloon animal. She’d snag a few remote-controlled cars, maybe a pony figurine or two; classics were always marketable. Bill started humming tunelessly, fiddling with a miniature grappling hook. "Think they have cake?" She sighed. "Bill, focus. This isn’t a picnic.” The sheer volume of plastic toys was overwhelming, almost depressing. It was a logistical nightmare. A mountain of yearning and glitter. “We need a diversion.”
created_at
"2026-02-20T19:55:29.106Z"
2/20/2026, 7:55:29 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
347
moderation_latency
(null)
generation_time
6939
tokens_prompt
93
tokens_completion
334
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
"5aef2a85-3d1c-4659-a522-98bbb5272c6a"
is_byok
false
latency
34
model_permaslug
"google/gemma-3-12b-it"
provider_name
"Crusoe"
status
429
1
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-RHoNF2LmNDse9JTwB8drc7lE"
is_byok
false
latency
45
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771617329-7nu5EBvTX8o1eCanfoLr"
upstream_id
"chatcmpl-RHoNF2LmNDse9JTwB8drc7lE"
total_cost
0.00003693
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
99.96%
Dialogue to Total Word Ratio
Ratio: 11.40%, Deviation: 1.40%
neededClean
false
wordsTotal
193
wordsDialogue
22
98.7946%