NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAWZQ17QP78CSED922V1HB
Run Details
Model:
Gemma 3 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.6s
Cost:
$0.000123
Provider:
Parasail
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
89.07%
Dialogue to Total Word Ratio
(details)
44.5332%
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. Factor that in.” “Glitter? What about the laser grid?” Bill adjusted his ridiculously oversized sunglasses. “Forget the laser grid, Bill! It’s a five-year-old’s birthday, not Fort Knox. It's crepe paper. Glitter gets in the eyes, distracts the adults. Classic misdirection.” “Right. Distraction. Because a room full of screaming kids isn’t distracting enough?” “It needs *layers*, Bill. Layers! We’re professionals, remember? Operation Birthday Bonanza requires finesse.” “Bonanza? Seriously?” “It’s catchy! Look, you handle the bouncy castle. Inflate it to maximum capacity, total chaos. I’ll sweep the presents. Focus on the bigger boxes. Lego, video games, anything resaleable.” “And what if a parent asks what we’re doing?” “Improvise! Say we're… professional gift organizers? We specialize in consolidating.” “Consolidating into *our* van?” “Details, Bill, details. Don’t get hung up on semantics. Just remember the glitter.” “Fine. Glitter. But I’m wearing goggles.”
created_at
"2026-02-20T20:12:16.493Z"
2/20/2026, 8:12:16 PM
model
"google/gemma-3-27b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
320
moderation_latency
(null)
generation_time
7536
tokens_prompt
93
tokens_completion
302
native_tokens_prompt
75
native_tokens_completion
260
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
0.000123
router
(null)
provider_responses
0
endpoint_id
"2f608ade-87b1-46ed-8ae7-2714dddf2abb"
id
"cmpl-5c561f89c0b8424c8224812866a7ba21"
is_byok
false
latency
205
model_permaslug
"google/gemma-3-27b-it"
provider_name
"Parasail"
status
200
api_type
"completions"
id
"gen-1771618336-Z1jESACIXZEb5I9NJZES"
upstream_id
"cmpl-5c561f89c0b8424c8224812866a7ba21"
total_cost
0.000123
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Parasail"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
144
89.07%
Dialogue to Total Word Ratio
Ratio: 95.83%, Deviation: 5.83%
neededClean
false
wordsTotal
144
wordsDialogue
138
44.5332%