NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9CMCEFHZA6BNA5QHFYSD5
Run Details
Model:
Gemma 3 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.5s
Cost:
$0.000046
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.81%
Dialogue to Total Word Ratio
(details)
49.9064%
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 remind me again why we’re risking jail time for… toys?” Bill asked, adjusting his ridiculous inflatable dinosaur costume. “Sentimentality, Bill. High-end sentimentality,” Molly retorted, examining a detailed map of a bouncy castle. “That’s little Timmy Vandergelt’s fifth birthday. Vandergelt as in *Vandergelt Industries* Vandergelt. Those presents? Solid gold Lego, antique porcelain dolls, probably a miniature pony.” “A pony in a gift box?” “Metaphorically, Bill. Focus! We go in during the magic show. Distraction is key.” “And the dinosaur?” “You blend. Kids love dinosaurs. You look harmlessly goofy.” “Harmlessly goofy isn’t exactly my brand, Molly.” “It is today. I handle the gift bags, you create a diversion. No sudden movements. No talking. Just… roar occasionally.” “Roar? Seriously?” “A little roar. It's festive! And Bill? No keeping any of the loot. I saw what happened with the bouncy castle incident last time.” “That was a *superior* bouncy castle!”
created_at
"2026-02-20T19:45:52.028Z"
2/20/2026, 7:45:52 PM
model
"google/gemma-3-27b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
447
moderation_latency
(null)
generation_time
7319
tokens_prompt
93
tokens_completion
289
native_tokens_prompt
75
native_tokens_completion
247
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
0.00004552
router
(null)
provider_responses
0
endpoint_id
"8f22002c-c045-446f-a1b9-9896133536b8"
id
"chatcmpl-RRNeZxifomqn8i0SOkPJ1eYu"
is_byok
false
latency
56
model_permaslug
"google/gemma-3-27b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771616752-mGUX77NdiqXNq99a1swh"
upstream_id
"chatcmpl-RRNeZxifomqn8i0SOkPJ1eYu"
total_cost
0.00004552
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
99.81%
Dialogue to Total Word Ratio
Ratio: 87.92%, Deviation: 2.08%
neededClean
false
wordsTotal
149
wordsDialogue
131
49.9064%