NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9A0A4BD6B0DF7WFD94093
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.3s
Cost:
$0.000023
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 Glitter Bomb is a go?” Molly asked, meticulously straightening a miniature plastic pirate sword on the greasy diner table. Bill stirred his coffee with unnerving intensity. “Absolutely. But we're going in fast, yeah? No lingering. I’m not comfortable with small children.” “Relax, Bill. They’re preoccupied with cake and screaming. Think of it as a low-stakes acquisition.” “Low stakes? We’re relieving a room full of kids of their *stuff*, Molly! It feels… wrong.” “Wrong is paying for Christmas. Remember the spreadsheet?” “The spreadsheet makes it worse! ‘Potential Return Rate: 78%.’ It’s terrifying!” He shuddered. “What if they miss us? What if they call security?” “Security’s comprised of a teenager asleep in the corner and a woman who clearly hates birthdays. Trust me. Just grab the biggest boxes. Think glitter, plushies, anything vaguely valuable.” “And what about the balloons?” “Balloons are a distraction. We’ll use them. Strategic balloon deployment.” Molly grinned, brandishing the pirate sword. “Let’s go snatch some presents.”
created_at
"2026-02-20T19:44:25.934Z"
2/20/2026, 7:44:25 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
300
moderation_latency
(null)
generation_time
3179
tokens_prompt
93
tokens_completion
306
native_tokens_prompt
75
native_tokens_completion
254
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
0.00002332
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RBAP2p1BhRZMArtaugrVLuiT"
is_byok
false
latency
158
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771616665-6sGmXq2BknCX4BVhpDP1"
upstream_id
"chatcmpl-RBAP2p1BhRZMArtaugrVLuiT"
total_cost
0.00002332
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
162
0.00%
Dialogue to Total Word Ratio
Ratio: 82.10%, Deviation: 32.10%
neededClean
false
wordsTotal
162
wordsDialogue
133
0.0000%