NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9YER20J5FSFZ74N5FDETJ
Run Details
Model:
Gemma 3 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.9s
Cost:
$0.000059
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
49.9996%
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
“Right, so glitter. We’re agreed, glitter is the enemy?” Molly asked, meticulously picking at a chipped fingernail. Bill sighed. “Molly, we’ve been over this. Glitter clings. Glitter reveals. Glitter is a forensic nightmare.” “But kids *love* glitter. It’ll be everywhere! Distraction!” “It’s a distraction *for us*, finding all the glitter. Focus. Laser pointers. Remember? Distract the adults with laser pointers while we bag the haul.” “Laser pointers feel…underwhelming for grand larceny.” “What were *you* thinking? Smoke bombs? A trained monkey?” “A monkey in a tiny tuxedo, actually. Very diverting.” “No monkeys. No glitter. Presents in, out, gone. Little Timmy's fifth birthday is our jackpot. All those remote control cars…” Bill’s eyes glazed over. “You just want the remote control cars, don’t you? It’s always the remote control cars.” “They're classic! And easily fenced.” “Fine, fine. Laser pointers it is. But if I see a single sequin, I’m out.”
created_at
"2026-02-20T19:55:36.076Z"
2/20/2026, 7:55:36 PM
model
"google/gemma-3-27b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
646
moderation_latency
(null)
generation_time
10879
tokens_prompt
93
tokens_completion
287
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
0.000059325
router
(null)
provider_responses
0
endpoint_id
"cf530f36-7cb8-4eb9-8953-880eef952af3"
id
"f75e1479-d0fe-47cb-a535-90ca0c36cadd"
is_byok
false
latency
522
model_permaslug
"google/gemma-3-27b-it"
provider_name
"Novita"
status
200
api_type
"completions"
id
"gen-1771617336-uBFrdGFUVyK8rQyToxiB"
upstream_id
"f75e1479-d0fe-47cb-a535-90ca0c36cadd"
total_cost
0.000059325
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
148
100.00%
Dialogue to Total Word Ratio
Ratio: 90.54%, Deviation: 0.54%
neededClean
false
wordsTotal
148
wordsDialogue
134
49.9996%