NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9DN3JWTCW679BSHD0C0HM
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.8s
Cost:
$0.000023
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
85.08%
Dialogue to Total Word Ratio
(details)
42.5410%
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, Operation Glitter Bomb is a go?" Molly asked, meticulously rearranging a stack of miniature pirate figurines. “Absolutely. But seriously, Molly, a children's party? This feels…excessive.” Bill shifted, clutching a blueprint of the venue – a bouncy castle shaped like a unicorn. “Excessive is good, Bill! Think of the possibilities! Fifteen-year-old boys will be ecstatic!” “Ecstatic about receiving a plastic dinosaur, maybe. Look, the security is surprisingly tight. Motion sensors, flashing lights, a balloon animal artist." “Details, details! Balloons are easily deflated. Motion sensors? We have smoke bombs.” “Smoke bombs inside a bouncy castle? Molly, that's just… chaotic.” “Chaotic is our brand! Okay, okay, ten minutes. I’ve got a team prepping distraction – a very enthusiastic rendition of ‘Happy Birthday’ on a recorder.” “A recorder? You’re kidding.” “Absolutely not. Top-tier auditory assault.” “Just…promise me we’re getting out with more than a handful of sparkly erasers.” “Bill, relax. Think of the joy!”
created_at
"2026-02-20T19:46:25.534Z"
2/20/2026, 7:46:25 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
171
moderation_latency
(null)
generation_time
2600
tokens_prompt
93
tokens_completion
299
native_tokens_prompt
75
native_tokens_completion
251
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
0.00002308
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-R16DAsevo1LyqY33CTsS2oU1"
is_byok
false
latency
47
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771616785-OlbTtBJiE21py0wIyWLs"
upstream_id
"chatcmpl-R16DAsevo1LyqY33CTsS2oU1"
total_cost
0.00002308
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
153
85.08%
Dialogue to Total Word Ratio
Ratio: 83.66%, Deviation: 6.34%
neededClean
false
wordsTotal
153
wordsDialogue
128
42.5410%