NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYB3WS9B1V01ST34WCR6JYH
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.5s
Cost:
$0.000022
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 pickle factory, a fitting soundtrack to our impending chaos. Bill meticulously arranged miniature plastic dinosaurs on a map of the Maplewood Elementary School gymnasium. Molly chewed on a toothpick, her gaze fixed on the flickering fluorescent light above. “Seriously, Bill? Dinosaurs?” she asked, her voice dry. “Strategic placement,” he replied, meticulously positioning a T-Rex beside the entrance. “Kids respond to prehistoric predators. Creates distraction. Redirection.” “Or just looks ridiculous,” Molly countered, popping the toothpick into her mouth. “We’re stealing birthday presents, not staging a Jurassic Park reenactment.” He ignored her, adding a Velociraptor to the plan near the cake table. “The cake is key, Molly. Sugar-fueled hysteria. Makes for easier acquisition.” “Acquisition? You’re talking about a room full of eight-year-olds, not a Fort Knox vault. What’s the angle, exactly?” “Operation ‘Happy Birthday Loot’ is proceeding according to schedule,” Bill stated, straightening a plastic Stegosaurus. “Now, about the inflatable bouncy castle…”
created_at
"2026-02-20T20:16:02.867Z"
2/20/2026, 8:16:02 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
198
moderation_latency
(null)
generation_time
3330
tokens_prompt
93
tokens_completion
314
native_tokens_prompt
75
native_tokens_completion
242
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
0.00002236
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-R5PY204f8jvFzD2lRdW98XVE"
is_byok
false
latency
73
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771618562-079ejkCIdOT3s5Xovcp3"
upstream_id
"chatcmpl-R5PY204f8jvFzD2lRdW98XVE"
total_cost
0.00002236
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
164
0.00%
Dialogue to Total Word Ratio
Ratio: 45.12%, Deviation: 35.12%
neededClean
false
wordsTotal
164
wordsDialogue
74
0.0000%