NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HHMX70CZ3J419WSV9SFXFX
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
16.3s
Cost:
$0.022674
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 lowered her binoculars from the hedge. "The perimeter is crawling with sticky ankle-biters, Bill. Is the bounce house neutralized?" "I unplugged the generator," Bill whispered, checking his tactical stopwatch. "The vinyl castle is collapsing. Pure pandemonium." "Brilliant. Now, the primary objective: the gift table. What are we looking at?" "Intel confirms three remote-controlled monster trucks, a motorized Barbie Corvette, and an absurd mountain of Lego." "Lego? We can’t step on that without tactical footwear!" "Relax. I wore three pairs of wool socks. What about Timmy?" "The birthday boy is hopped up on blue frosting and swinging a foam sword. Wildcard status, but manageable." "Did you neutralize the parents?" Bill asked. "I pushed a runaway mimosa cart down the driveway. Every suburban mom is sprinting to intercept." "Ruthless, Molly. Absolutely cold-blooded." "I do what the job demands. Did you bring our extraction vehicle?" "The red Radio Flyer wagon is hidden behind the hydrangeas." "Good. Once we breach the patio, we bag the loot and retreat under the trampoline." "And what if the clown tries to be a hero?" "Pocket glitter straight to the retinas. Works every single time." Molly grinned, zipping her duffel sack. "Let's ruin a seven-year-old’s Tuesday."
created_at
"2026-09-02T17:11:13.384Z"
9/2/2026, 5:11:13 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1353
moderation_latency
(null)
generation_time
16309
tokens_prompt
75
tokens_completion
1588
native_tokens_prompt
67
native_tokens_completion
6033
native_tokens_completion_images
0
native_tokens_reasoning
5727
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
0.022674
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788369073-fnfYENgn5RcNzjqlLN9F"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788369073-S9TqxFi79YNLUXriUpvT"
upstream_id
"sViYau_3G7qb_uMP05yQyQ4"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"sViYau_3G7qb_uMP05yQyQ4"
is_byok
false
latency
1353
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.022674
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: 89.71%, Deviation: 0.29%
neededClean
false
wordsTotal
204
wordsDialogue
183
99.9995%