NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8M5K04VG2ZAFJJH469EBF
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.3s
Cost:
$0.000024
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
10.0948%
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 rain hammered against the corrugated iron roof of the abandoned warehouse, a soundtrack to our increasingly ludicrous plan. Molly traced a finger across the blueprint – a ridiculously detailed schematic of “Princess Sparkle’s Unicorn Extravaganza” held at the community hall. “Right, so the pressure sensors are surprisingly calibrated to the rhythm of a five-year-old’s bouncing,” she said, meticulously highlighting a point with a chewed-up pencil. “We’ll need to time our entry precisely with Little Timmy’s rendition of ‘Happy Birthday.’” Bill, a man built like a slightly deflated rhinoceros, shifted his weight. “And the laser grid? You’re sure it's programmed to register glitter?” “Absolutely. Mrs. Higgins, bless her polyester heart, is obsessed with sparkle. It’s basically a disco for rodents.” Molly tapped the blueprint again. “I’ve factored in the inevitable sugar rush. Everyone anticipates hyperactivity. It's a major variable.” Bill stared at the image of a room brimming with brightly wrapped packages. "Just...a lot of presents, huh?" “A glorious, shimmering mountain of juvenile delight,” Molly confirmed, a disturbing glint in her eye. “Operation Unicorn Loot is a go.”
created_at
"2026-02-20T19:32:30.52Z"
2/20/2026, 7:32:30 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
151
moderation_latency
(null)
generation_time
2982
tokens_prompt
93
tokens_completion
328
native_tokens_prompt
75
native_tokens_completion
263
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
0.00002404
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RGQyWL2aw5SQDnO9BklhLi8R"
is_byok
false
latency
53
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771615950-pr1PUipIZlSSFZcWvk4w"
upstream_id
"chatcmpl-RGQyWL2aw5SQDnO9BklhLi8R"
total_cost
0.00002404
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
0.00%
Dialogue to Total Word Ratio
Ratio: 52.78%, Deviation: 42.78%
neededClean
false
wordsTotal
180
wordsDialogue
95
10.0948%