NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYA563W61A1J9YZ1HWJQ5VG
Run Details
Model:
Gemma 3 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.4s
Cost:
$0.000046
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
97.57%
Dialogue to Total Word Ratio
(details)
48.7858%
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
“Okay, so glitter. Everywhere,” Molly stated, sketching furiously in a notepad. Bill sighed. “Glitter is a certainty, Mol. It’s a children’s party. But are you *planning* for the glitter, or just acknowledging its inevitable existence?” “Planning! Operation: Present Plunder hinges on glitter distraction. Tiny hands, sparkly chaos, nobody notices two adults scooping up Lego and Barbies.” “Scooping? You make it sound like ice cream. We’re strategically relocating gifts, Molly.” “Semantics, Bill. So, you’re handling the bouncy castle diversion?” “Someone has to. I'm thinking a strategically timed ‘Oh no, it’s deflating!’ should give us five minutes, tops.” “Five minutes to liberate a mountain of plastic? Ambitious, even for you.” “Hey, I’ve timed a bouncy castle deflation before. It's a skill. What about the parents?” “They’ll be engrossed in awkward small talk and lukewarm pizza. Trust me. We're ghosts, Bill. Gift-acquiring ghosts.” “Just promise me no face paint.” “No promises.”
created_at
"2026-02-20T19:59:16.612Z"
2/20/2026, 7:59:16 PM
model
"google/gemma-3-27b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1010
moderation_latency
(null)
generation_time
12342
tokens_prompt
93
tokens_completion
293
native_tokens_prompt
75
native_tokens_completion
252
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
0.00004632
router
(null)
provider_responses
0
endpoint_id
"8f22002c-c045-446f-a1b9-9896133536b8"
id
"chatcmpl-Rtd7w9vfxtl5qmgdSoVfQdN2"
is_byok
false
latency
58
model_permaslug
"google/gemma-3-27b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771617556-gPjweORmnA87mWYxiB5W"
upstream_id
"chatcmpl-Rtd7w9vfxtl5qmgdSoVfQdN2"
total_cost
0.00004632
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
149
97.57%
Dialogue to Total Word Ratio
Ratio: 93.96%, Deviation: 3.96%
neededClean
false
wordsTotal
149
wordsDialogue
140
48.7858%