NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7ZVM0HJ0GVG63VQNCA0W9
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.2s
Cost:
$0.000024
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.5180%
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 frantic, percussive counterpoint to Molly’s meticulous spread of maps and sticky notes. A chaotic archipelago of glittery wrapping paper scraps dotted the table, remnants of a previous, less-successful operation. Bill, a man built like a slightly disgruntled badger, was attempting to eat a large cheese and pickle sandwich, crumbs clinging to his already stained tweed jacket. “Right, so the ‘Rainbow Rhapsody’ party. Five-year-olds,” Molly stated, tapping a brightly colored map with a red pen. “High risk, potentially high reward. Primarily, we’re after the presents.” Bill chewed thoughtfully, a fleck of pickle dangling from his lip. “Five-year-olds. That’s… specific.” “Specificity is key, Bill. Their parents will be distracted. Balloons. Music. Excessive sugar. A perfect cocktail of blissful obliviousness.” She pointed to a cluster of notes labeled ‘Distraction Tactics’. “I’m thinking a rogue magician. A surprisingly grumpy clown. Perhaps a synchronized swimming routine?” Bill swallowed hard. “Synchronized swimming? Molly, are you mad?” “Just brainstorming, darling. Now, about the ventilation shaft…”
created_at
"2026-02-20T19:21:24.875Z"
2/20/2026, 7:21:24 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
146
moderation_latency
(null)
generation_time
2640
tokens_prompt
93
tokens_completion
327
native_tokens_prompt
75
native_tokens_completion
260
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
0.0000238
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RrXZ7e3OYSwvabkF0qFTFnSt"
is_byok
false
latency
55
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771615284-mOXnet2gdSGLevJHg6hs"
upstream_id
"chatcmpl-RrXZ7e3OYSwvabkF0qFTFnSt"
total_cost
0.0000238
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
1.04%
Matches word count
n/a
neededClean
false
words
174
0.00%
Dialogue to Total Word Ratio
Ratio: 40.80%, Deviation: 30.80%
neededClean
false
wordsTotal
174
wordsDialogue
71
0.5180%