NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HGASGYZ3ZVNNH8EKMP0CN3
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
18.2s
Cost:
$0.022277
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Bill adjusted his binoculars, peering through the dirty windshield of their parked minivan at the suburban front yard. Rainbow streamers fluttered innocently across the white picket fence. Somewhere beneath that pastel nightmare lay forty boxes of pure consumer greed, completely unguarded by anyone taller than four feet. Molly rolled out a blueprint on the dashboard, weighing down the corners with stolen cupcakes. She tapped a highlighter menacingly against the target zone. "The bounce house provides tactical elevation," she whispered, her eyes ablaze with professional criminal intensity. Bill shook his head, checking the timer on his cheap digital watch. A clown had just crossed the perimeter with balloon swords, complicating their parameters. "Those toddlers will tear you apart," he muttered. Molly sneered, pulling a bandolier of organic apple juice pouches from beneath her beige trench coat. Her tactical preparation was beyond reproach. Every contingency had been mapped, from sugar crashes to sudden tantrums. "Not if I deploy the juice boxes first," she said. Victory was practically guaranteed. The ultimate toy haul of the century awaited them just beyond the sprinkler system. Bill revved the engine, snapped his ski mask into place, and prepared to ruin one little seventh birthday party forever.
created_at
"2026-09-02T16:48:13.539Z"
9/2/2026, 4:48:13 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1766
moderation_latency
(null)
generation_time
17926
tokens_prompt
75
tokens_completion
1796
native_tokens_prompt
67
native_tokens_completion
5927
native_tokens_completion_images
0
native_tokens_reasoning
5680
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
"default"
usage
0.0222765
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788367693-QD5OyQGXNoJwH9FZADpa"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788367693-miwoYENXC875MBtbkGYd"
upstream_id
"TVOYauW_KIz2jMcPr7DHyQ8"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"TVOYauW_KIz2jMcPr7DHyQ8"
is_byok
false
latency
1766
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.0222765
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%