NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HH9YWKEWWZMJXK9KR7B1KN
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.0s
Cost:
$0.015174
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9995%
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
Molly adjusted her polka-dot bow tie. "Put the squeaky nose on, Bill." "I refuse. A master burglar never wears a squeaky nose on a high-stakes job." "You are Barnaby the Clown today, so squeak with professional authority." Bill sighed and crossed his arms. "Fine. What's our tactical entry vector?" "The bouncy castle flank. The perimeter sentry is Timmy's grandmother, currently incapacitated by three glasses of sparkling cider." "And the primary target location?" "The main gift table sits between the chocolate fountain and the miniature pony." "A pony? Molly, that introduces severe logistical hazards! What if the beast bites?" "Feed it a baby carrot, you coward. Playground chatter confirms Timmy scored two motorized mini-tractors, three gaming consoles, and an antique train set." "Sweet mother of pearl. How do we haul that out?" "We cram everything into the bottomless magic duffel. If toddlers swarm the perimeter, deploy the tactical glitter smoke screen." "Understood. Can we snatch the ice cream cake too?" "Bill, frosting leaves forensic evidence! We strike precisely when the unicorn piƱata ruptures. Total sugar-fueled anarchy. We grab the loot and vanish in the stampede." He grimaced, honking the foam nose twice. "Genius, Molly. Let's go rob an unsuspecting seven-year-old."
created_at
"2026-09-02T17:05:14.65Z"
9/2/2026, 5:05:14 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2524
moderation_latency
(null)
generation_time
13926
tokens_prompt
75
tokens_completion
1580
native_tokens_prompt
67
native_tokens_completion
4033
native_tokens_completion_images
0
native_tokens_reasoning
3729
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
0.015174
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788368714-rmMsq1u3E9d0vcXXkrSa"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788368714-e0EMoEOq45JBrVoAh7wC"
upstream_id
"SleYapCvK-G8_uMPhJHN-AI"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"SleYapCvK-G8_uMPhJHN-AI"
is_byok
false
latency
2524
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.015174
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
199
100.00%
Dialogue to Total Word Ratio
Ratio: 90.24%, Deviation: 0.24%
neededClean
false
wordsTotal
205
wordsDialogue
185
99.9995%