NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY987R9EMYHF9FKDKJ20X8M
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.1s
Cost:
$0.000023
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.84%
Dialogue to Total Word Ratio
(details)
49.9201%
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, meticulously sketching on a napkin. “Absolutely a diversion. Kid distraction level eight,” Bill replied, adjusting his spectacles. “But the presents… they’re stacked by the cake table, aren’t they?” “Confirmed. Mountains of plastic dinosaurs and sparkly unicorns. Honestly, the sheer volume is obscene.” “Obscene is good. Means more profit. Do you think we should wear clown noses?” “Bill, seriously? We’re going for a professional, subtle operation. Not a circus.” “Subtle? Molly, we’re infiltrating a party for five-year-olds. ‘Subtle’ went out the window with the last sticky bun.” “Fine. But no honking horns. Remember the fiasco at the ferret convention?” “Point taken. Just… a little shimmer? Like, a subtle glitter bomb?” “Absolutely not. Consider it a tactical no. Now, let's talk about backup exits. I’m thinking the tuba?” “The tuba? Are you insane?” “It's shiny! And it makes a loud noise. Perfectly thematic.”
created_at
"2026-02-20T19:43:28.021Z"
2/20/2026, 7:43:28 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
173
moderation_latency
(null)
generation_time
2986
tokens_prompt
93
tokens_completion
285
native_tokens_prompt
75
native_tokens_completion
245
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
0.0000226
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RcypQ9Gg3hT72bc9LARH8NtA"
is_byok
false
latency
53
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771616608-LmOE8zsvgPvewu64ChwV"
upstream_id
"chatcmpl-RcypQ9Gg3hT72bc9LARH8NtA"
total_cost
0.0000226
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
150
99.84%
Dialogue to Total Word Ratio
Ratio: 92.00%, Deviation: 2.00%
neededClean
false
wordsTotal
150
wordsDialogue
138
49.9201%