NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYANFDJA8NNJN2JY3BMMRGY
Run Details
Model:
Gemma 3 12B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.8s
Cost:
$0.000038
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
1.63%
Dialogue to Total Word Ratio
(details)
7.9641%
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 cast a lurid pink glow across the alleyway, reflecting in Molly’s overly dramatic eye makeup. Bill chewed on a toothpick, surveying the scene opposite. It was a veritable explosion of sugar and tiny humans. “Right then,” Molly declared, adjusting her ridiculously oversized sunglasses. “Operation Sugar Rush is a go. Think their security is tight?” “Security? Molly, it’s a five-year-old’s birthday party. I’m more worried about rogue glitter bombs,” Bill replied, spitting the toothpick into a puddle. “Though, a rogue glitter bomb *would* be inconvenient.” “Don’t be ridiculous, Bill. We're professionals. We need to strategize. I’m thinking I distract the adults with…a lost puppy?” Molly suggested, wrinkling her nose. “A lost puppy? Seriously? They’ll probably give it cake. We’re here for the Lego, Molly, the Lego! Let me handle the distraction; I’ll pretend to be a magician.” “A magician? You? Last time you tried to do magic, you pulled a live pigeon out of a hat.” Molly’s voice rose slightly. Bill shrugged. “Well, the kids seemed to like it. Focus, Molly! Presents. Lego. Go.”
created_at
"2026-02-20T20:08:10.432Z"
2/20/2026, 8:08:10 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
326
moderation_latency
(null)
generation_time
7738
tokens_prompt
93
tokens_completion
311
native_tokens_prompt
75
native_tokens_completion
273
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
0.00003849
router
(null)
provider_responses
0
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-RBn0k8MI5QxgO4vAqp5MPQZE"
is_byok
false
latency
54
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771618090-unH7V1LAQgbC96u5tSr0"
upstream_id
"chatcmpl-RBn0k8MI5QxgO4vAqp5MPQZE"
total_cost
0.00003849
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
14.30%
Matches word count
n/a
neededClean
false
words
179
1.63%
Dialogue to Total Word Ratio
Ratio: 64.25%, Deviation: 14.25%
neededClean
false
wordsTotal
179
wordsDialogue
115
7.9641%