NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYB1RDZ37D8KXQV6W7Z80E7
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.8s
Cost:
$0.000022
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.72%
Dialogue to Total Word Ratio
(details)
49.8584%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
“Right, so, the bouncy castle?” Molly asked, chewing on the end of a pen. “Seriously? The bouncy castle? Are you suggesting we infiltrate a three-year-old’s birthday party through a giant inflatable blob?” Bill groaned. “It’s a distraction, Bill! Think about it. Parents distracted, kids bouncing. Presents unguarded. Pure chaos.” “Chaos is your middle name, Molly. Mine’s ‘slightly panicked.’” “Don’t be dramatic. Okay, next question: frosting. Do we go for chocolate or vanilla?” “Chocolate. Always chocolate. It’s… persuasive.” “Persuasive for *who*, exactly? The toddlers?” “Look, the point is, secured chocolate frosting equals a slower inspection process.” “And how do we get *in*?” “I’ve procured a miniature pirate costume. Think we can convince the birthday boy we’re looking for buried treasure?” “A pirate? Molly, this is a party, not ‘Pirates of the Caribbean.’” “Details, details. It'll buy us time. Now, about those presents…”
created_at
"2026-02-20T20:14:52.874Z"
2/20/2026, 8:14:52 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
177
moderation_latency
(null)
generation_time
3718
tokens_prompt
93
tokens_completion
283
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-RdPqH4zLJu2DiTDBMszD3sVW"
is_byok
false
latency
64
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771618492-i2nCgP2PqJyRzxt0YoMU"
upstream_id
"chatcmpl-RdPqH4zLJu2DiTDBMszD3sVW"
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
143
99.72%
Dialogue to Total Word Ratio
Ratio: 92.31%, Deviation: 2.31%
neededClean
false
wordsTotal
143
wordsDialogue
132
49.8584%