NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY81MDSMDH2WSMWBZH8WY27
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.6s
Cost:
$0.000022
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.66%
Dialogue to Total Word Ratio
(details)
49.8276%
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
“Seriously, a bouncy castle?” Molly asked, wrinkling her nose. “It’s a *themed* bouncy castle, Molly. ‘Pirate Adventure.’ Think of the glitter.” Bill replied, tapping his chin. “Glitter is the enemy. It gets *everywhere*. We’re after teddy bears, Bill, not sequins.” “But the parents… they’re distracted. Face painting, cake… vulnerable.” “Vulnerable to what? A rogue balloon animal?” “No! To a coordinated present procurement! We’re talking Baby Shark plushies, gigantic LEGO sets… a lifetime supply of slime!” “Slime? You’re losing me. Are you sure this is worth it?” “Absolutely. Imagine the resale value. Think of the chaos!” “Chaos? Bill, we’re stealing from a *birthday party*.” “Precisely! A glorious, sugar-fueled chaos! Now, about the distraction…” “Let's just get in and out. No improvisational pirate battles, understood?” “Understood. Though, a little swashbuckling might be beneficial.”
created_at
"2026-02-20T19:22:23.044Z"
2/20/2026, 7:22:23 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
99
moderation_latency
(null)
generation_time
2458
tokens_prompt
93
tokens_completion
272
native_tokens_prompt
75
native_tokens_completion
239
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
0.00002212
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RNSpjc43Z51iLu6UGWLZlv5Q"
is_byok
false
latency
24
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771615343-FgknGIZLAQLVq3EC4V1p"
upstream_id
"chatcmpl-RNSpjc43Z51iLu6UGWLZlv5Q"
total_cost
0.00002212
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
132
99.66%
Dialogue to Total Word Ratio
Ratio: 92.42%, Deviation: 2.42%
neededClean
false
wordsTotal
132
wordsDialogue
122
49.8276%