NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7NX5MEKJ1EFV1D6DAPHD5
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.0s
Cost:
$0.000022
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
96.01%
Dialogue to Total Word Ratio
(details)
48.0038%
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. Seriously?” Bill asked, adjusting his ridiculously oversized fedora. “It’s the key, Bill! The key! Think about the logistics. Balloons, sugar, panicked parents – perfect distraction.” Molly tapped a pen against a meticulously drawn floorplan of the community hall. “Distraction? I’m thinking more about the sheer volume of stuffed animals. Do you even *know* how many teddy bears we’re talking about?” “Approximately three hundred, give or take a unicorn. It’s a lucrative market, Bill. Think 'vintage plushies’." “Vintage plushies! Molly, we’re stealing birthday presents!” “We're acquiring curated childhood nostalgia, darling. Besides, Mrs. Higgins specifically requested 'lots of bright things.' It’s practically an invitation.” “An invitation to sticky fingers and potential glitter lawsuits.” “Details, details. Okay, you’re on inflatable monitoring. I’m going for the loot.” “Wait, what about the cake?” “Don’t even *think* about the cake.”
created_at
"2026-02-20T19:15:58.781Z"
2/20/2026, 7:15:58 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
220
moderation_latency
(null)
generation_time
2872
tokens_prompt
93
tokens_completion
284
native_tokens_prompt
75
native_tokens_completion
236
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
0.00002188
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RZfvpbDb3kSMQCEXBeF2S0W0"
is_byok
false
latency
112
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771614958-bbbPnov98NjyBSudnxiJ"
upstream_id
"chatcmpl-RZfvpbDb3kSMQCEXBeF2S0W0"
total_cost
0.00002188
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
138
96.01%
Dialogue to Total Word Ratio
Ratio: 85.51%, Deviation: 4.49%
neededClean
false
wordsTotal
138
wordsDialogue
118
48.0038%