NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYB00CCRBHXZAXESKR15JMG
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.5s
Cost:
$0.000024
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 Sugar Rush. Let’s run it again,” Molly said, meticulously taping a miniature map of the community hall to the greasy diner table. “Seriously, Molly? A children’s party? We’re risking jail time for… stuffed animals?” Bill grumbled, picking at a cold french fry. “Don’t be ridiculous. It’s not the stuffed animals, Bill. It’s the *potential*. Think of the resale value! Vintage Beanie Babies, probably. And the glitter!” “Glitter is a biohazard. You realize that, right?” “Details, details. Okay, I disable the security cameras – focusing on the pixar themed ones, obviously – you handle the door. We go in, grab the presents, and out. Discreetly. Like ninjas.” “Ninjas who wear camouflage sweaters and are slightly terrified of children. What if a kid asks us what we're doing?" “Just say we’re… evaluating the party decorations! Yes! We’re evaluating the decorations. Now, about the helium balloons…” “Let’s just get this over with. Can we at least get some napkins?”
created_at
"2026-02-20T20:13:55.478Z"
2/20/2026, 8:13:55 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
175
moderation_latency
(null)
generation_time
3319
tokens_prompt
93
tokens_completion
284
native_tokens_prompt
75
native_tokens_completion
257
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
0.00002356
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RGwbnnnVmHm6YeCD5kZYFZZ9"
is_byok
false
latency
57
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771618435-ttHreGoSc5syUntUU1b7"
upstream_id
"chatcmpl-RGwbnnnVmHm6YeCD5kZYFZZ9"
total_cost
0.00002356
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
157
0.00%
Dialogue to Total Word Ratio
Ratio: 84.71%, Deviation: 34.71%
neededClean
false
wordsTotal
157
wordsDialogue
133
0.0000%