NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAD2WW3585NNSXRBKJR3AK
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.8s
Cost:
$0.000162
Provider:
Cloudflare
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0009%
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 and blue monstrosity against the suburban twilight. Molly chewed on a licorice whip, surveying the scene. “Right, Bill. Operation Sugar Rush is a go. You still got the distraction device?” Bill patted his oversized pockets. “Naturally. A trained squirrel, dressed as a miniature Elvis. Guaranteed to draw attention.” Molly raised an eyebrow. “A squirrel? Elvis? Really, Bill?” “Hey, it’s memorable! Besides, kids love squirrels. And Elvis. It’s a winning combination.” He winked. “While they’re distracted by ‘Hound Dog’ and nut-gathering, we swoop in. You handle the teddy bears, I’ll take the remote-controlled cars.” “And the Lego?” Molly asked, already picturing mountains of plastic bricks. “Lego’s mine too. Think of the resale value! We’ll be swimming in plastic gold.” Bill grinned, adjusting his fake mustache. “Just… try not to get caught petting the squirrel, alright? It bites.” “Wouldn’t dream of it. Let’s get rich, Bill.”
created_at
"2026-02-20T20:03:35.461Z"
2/20/2026, 8:03:35 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
383
moderation_latency
(null)
generation_time
3670
tokens_prompt
93
tokens_completion
283
native_tokens_prompt
75
native_tokens_completion
243
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
0.00016233
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
"08ebad49-bed1-4149-850c-d24e3c1d2084"
id
"id-1771617815810"
is_byok
false
latency
332
model_permaslug
"google/gemma-3-12b-it"
provider_name
"Cloudflare"
status
200
api_type
"completions"
id
"gen-1771617815-za3u6dzKuKJv10vy9Fer"
upstream_id
"id-1771617815810"
total_cost
0.00016233
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Cloudflare"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
154
0.00%
Dialogue to Total Word Ratio
Ratio: 68.18%, Deviation: 18.18%
neededClean
false
wordsTotal
154
wordsDialogue
105
0.0009%