NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYBAD3X2Y7DQ1MWC3BB8FZ1
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.7s
Cost:
$0.000025
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
30.1376%
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 bakery, a relentless, greasy rhythm. Molly, a woman whose enthusiasm perpetually outweighed her common sense, was meticulously arranging miniature plastic dinosaurs on a sticky table. Bill, a man whose face seemed permanently sculpted into a state of weary cynicism, watched her with undisguised disapproval. “You’re seriously presenting a geological survey to the targets, Bill?” he asked, his voice dry as week-old bread. Molly didn’t look up. “It’s reconnaissance! We need to understand the terrain. The strategic placement of the bouncy castle, the proximity of the cake table… crucial intel.” "Right," Bill grunted, kicking at a loose floorboard. “And you’ve identified this as a viable target based on…what? A flyer advertising ‘Princess Penelope’s Pre-Birthday Extravaganza’?” “It’s targeted glitter, Bill! Think of the possibilities! A hundred shiny, individually wrapped delights! We’re talking pure, unadulterated sucrose heist!” She gestured dramatically with a plastic T-Rex. “Besides, kids never suspect a dinosaur.” Bill sighed, rubbing his temples. "Just… let's focus on getting in and out without anyone noticing a seven-year-old’s birthday party is being robbed."
created_at
"2026-02-20T20:19:36.201Z"
2/20/2026, 8:19:36 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
161
moderation_latency
(null)
generation_time
3537
tokens_prompt
93
tokens_completion
340
native_tokens_prompt
75
native_tokens_completion
281
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
0.00002548
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RsjJ9kdPBgL4OWr6tgh6qOvD"
is_byok
false
latency
68
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771618776-iPcMp94RMIDMKnJVMn0r"
upstream_id
"chatcmpl-RsjJ9kdPBgL4OWr6tgh6qOvD"
total_cost
0.00002548
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
185
0.00%
Dialogue to Total Word Ratio
Ratio: 52.97%, Deviation: 42.97%
neededClean
false
wordsTotal
185
wordsDialogue
98
30.1376%