NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-20-01KS25XW4C1B1QADXQV4Q854XQ
Run Details
Model:
Gemini 3.5 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.4s
Cost:
$0.002324
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
43.1902%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly adjusted her binoculars, staring at the bouncy castle. We go in when the magician starts his show. That gives us exactly twelve minutes to sweep the gift table. Bill shook his head, chewing on a pastel-colored lollipop. Twelve minutes? That wizard looks like he knows his stuff. What if he does the endless scarf trick? That could delay the cake by ten. We do not have ten minutes, Bill. The clown is already eyeing us from the balloon station. Did you pack the distraction? I brought the supreme juice boxes, Bill whispered, tapping his tactical vest. Sixty percent real juice. They will tear each other apart for these. Perfect. While the toddlers riot over high-fructose corn syrup, we bag the loot. Remember, prioritize the big boxes. What about the gift bags? Some of those have giant bows. Bows are amateur, Bill. We want Lego sets. If I see one more handmade card, I will scream. Got it. High-value plastic only. Do we have a getaway plan? Molly smiled, pulling a key card from her pocket. The pony trailer out back is unlocked. We ride at three o'clock sharp.
created_at
"2026-05-20T07:52:13.201Z"
5/20/2026, 7:52:13 AM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
668
moderation_latency
(null)
generation_time
2299
tokens_prompt
77
tokens_completion
283
native_tokens_prompt
67
native_tokens_completion
247
native_tokens_completion_images
0
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
service_tier
"standard"
usage
0.0023235
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"LWgNavn7FPec1MkPi9LawQg"
is_byok
false
latency
668
model_permaslug
"google/gemini-3.5-flash-20260519"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer
(null)
request_id
"req-1779263533-CznOK8Pb4V6l1D0qGZpU"
session_id
(null)
api_type
"completions"
id
"gen-1779263533-vfL36GLeUwUggYWR6cyB"
upstream_id
"LWgNavn7FPec1MkPi9LawQg"
total_cost
0.0023235
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
189
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 50.00%
neededClean
false
wordsTotal
192
wordsDialogue
0
43.1902%