NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY97DQ8E2347GGCBXEH8ZED
Run Details
Model:
Gemma 3 4B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.0s
Cost:
$0.000023
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.57%
Dialogue to Total Word Ratio
(details)
49.7832%
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, bouncy castle, check. Clown with a suspiciously large pocket, double check,” Molly said, pacing. “We’re going in through the ventilation shaft, obviously.” “Ventilation shaft? Molly, seriously? That sounds…drafty,” Bill replied, fiddling with a miniature grappling hook. “Couldn't we just, you know, charm our way in? ‘Lost our tickets, terribly sorry, could we possibly admire the presents?’” “Charm? Bill, we’re stealing birthday presents! That’s not charming, that’s…desperate. Besides, the parents are glued to juice boxes. Think about the chaos!” “Chaos is my specialty. But I'm just saying, maybe a strategically placed glitter bomb? Distraction?” “Glitter? Bill, we’re aiming for a quick grab, not an intervention. Just focus on the stapler. You’re disabling the security camera with the stapler, right?” “Yep. Industrial strength. Should take out the whole system. Unless they upgraded. Do you think they upgraded?” “Don’t even *think* about it, Bill. Just the stapler. And silence.”
created_at
"2026-02-20T19:43:01.364Z"
2/20/2026, 7:43:01 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
165
moderation_latency
(null)
generation_time
2825
tokens_prompt
93
tokens_completion
283
native_tokens_prompt
75
native_tokens_completion
248
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
0.00002284
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RdK8mf9sntO4FT9ORZZGt1CM"
is_byok
false
latency
51
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771616581-FoyljwxAk1yET3b8d25o"
upstream_id
"chatcmpl-RdK8mf9sntO4FT9ORZZGt1CM"
total_cost
0.00002284
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
148
99.57%
Dialogue to Total Word Ratio
Ratio: 92.57%, Deviation: 2.57%
neededClean
false
wordsTotal
148
wordsDialogue
137
49.7832%