NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYB735BG3S2P0HYQZ1EH8BX
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.2s
Cost:
$0.000022
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
50.0000%
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, rainbow streamers, inflatable dinosaurs, and a frankly alarming amount of glitter?” Molly asked, meticulously sketching on a napkin. “Yep. The target is a seven-year-old named Timmy,” Bill replied, adjusting his ridiculous fake mustache. “Obsessed with pirate treasure. Irony, isn’t it?” “Absolutely. ‘Operation Sparkle Plunder.’ Sounds terribly childish, doesn’t it?” “It's efficient. We go in through the bouncy castle entrance. Less security.” “Less alarms, more sticky carpet. Are you seriously bringing the suction cups?” “Of course! Think of the presents, Molly! Think of the *value*!” “The value of a build-a-bear and a drone?” “Don’t be a party pooper. We need a distraction. I was thinking a dramatic rendition of 'Happy Birthday'?” “Bill, absolutely not. I’ll deploy the glitter bomb.” “Excellent! And the getaway vehicle?” “The clown car, obviously.” “Brilliant. Just… try not to traumatize the birthday boy, okay?”
created_at
"2026-02-20T20:17:47.704Z"
2/20/2026, 8:17:47 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
229
moderation_latency
(null)
generation_time
2886
tokens_prompt
93
tokens_completion
279
native_tokens_prompt
75
native_tokens_completion
238
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
0.00002204
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RyEaaE3DyLnb5yE92aeKVMeD"
is_byok
false
latency
113
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771618667-mh2o71r1jZTF6ZKDfm5I"
upstream_id
"chatcmpl-RyEaaE3DyLnb5yE92aeKVMeD"
total_cost
0.00002204
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
100.00%
Dialogue to Total Word Ratio
Ratio: 90.21%, Deviation: 0.21%
neededClean
false
wordsTotal
143
wordsDialogue
129
50.0000%