NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9RMA41MV7G14GQM1SRZ4B
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.4s
Cost:
$0.000025
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
The rain hammered against the corrugated iron roof of the abandoned laundromat, mirroring the frantic drumming in Molly’s chest. Across the table, Bill meticulously sharpened a ridiculously ornate letter opener. It looked less like a tool for opening envelopes and more like a miniature, silver dagger. “Right, so, the clown’s distraction,” she said, tapping a crumpled blueprint of the community hall. “We go in through the ventilation shaft. Tight squeeze, but I’ve worked on my flexibility.” Bill didn’t look up. "Flexibility is overrated. Precision is key. We need to be in and out before little Timmy starts demanding a second cupcake. This isn’t some grand larceny, Molly, it’s a targeted acquisition of brightly wrapped, sugar-laden delights.” He finally glanced at her. “You’re seriously considering wearing that sequined jumpsuit?” “It’s festive,” she countered, adjusting the shimmering fabric with a shrug. “And it confuses the security cameras. They think I’m part of the entertainment.” “They’ll think we’re insane,” Bill muttered, resuming his sharpening. “Just… try not to trip over any bouncy castles.” A long silence hung between them, punctuated only by the rain and the scrape of steel on steel. “Do you think they’ll have those unicorn ones?”
created_at
"2026-02-20T19:52:25.167Z"
2/20/2026, 7:52:25 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
158
moderation_latency
(null)
generation_time
3209
tokens_prompt
93
tokens_completion
344
native_tokens_prompt
75
native_tokens_completion
278
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
0.00002524
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-R8GHO2u88juLP8Bh1HfSOtaO"
is_byok
false
latency
51
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771617145-m0aW1nhsxaY6HQagw7rj"
upstream_id
"chatcmpl-R8GHO2u88juLP8Bh1HfSOtaO"
total_cost
0.00002524
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
0.00%
Dialogue to Total Word Ratio
Ratio: 50.76%, Deviation: 40.76%
neededClean
false
wordsTotal
197
wordsDialogue
100
49.9595%