NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HH1ZF6REJKAQ9G5XZQGYEY
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.0s
Cost:
$0.011109
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
99.96%
Dialogue to Total Word Ratio
(details)
99.3354%
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
"The bounce house goes up at two, Bill. That's our five-minute window." "Are you completely sure about these clown outfits, Molly? The giant polka-dot shoes squeak whenever I pivot," Bill whispered nervously. "Wrap them in duct tape," she muttered, peering through the binoculars. "Fine. But what about the mother? Linda is vigilant." "Juice-box replenishment will keep Linda trapped inside the kitchen." "And the kids? They’re vicious, Molly. Like tiny, sticky, caffeinated badgers." "Deploy the cupcakes. The ones loaded with blue sprinkles. Sugar shock hits them in thirty seconds, and while they're paralyzed, you bag the haul." "Do we go for the gift pile near the pony?" "Forget the pony, Bill! Target the gazebo. We want the shiny boxes, the heavy rectangles, anything indicating high-end robotics or video games." "I spotted a toddler clutching a velvet bag earlier." "That was a snack pouch, you moron." "It jingled like diamonds, Molly!" Molly pinched the bridge of her nose. "It was pretzel sticks! Focus. We breach the perimeter behind the plastic slide, shove the birthday loot into our burlap sacks, and vault the fence." "Can I keep the oversized plush giraffe?" "Only if it fits in the getaway wagon," she sighed. "Now put the red nose on. It’s showtime."
created_at
"2026-09-02T17:00:53.102Z"
9/2/2026, 5:00:53 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1147
moderation_latency
(null)
generation_time
9940
tokens_prompt
75
tokens_completion
1093
native_tokens_prompt
67
native_tokens_completion
2949
native_tokens_completion_images
0
native_tokens_reasoning
2641
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
0.011109
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788368453-t5F6m9m031AV0y21Cdfn"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788368453-LJ1yDWBrSCbHFonIyrcA"
upstream_id
"RVaYaoa-Cqyb_uMP-4PkiQ8"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"RVaYaoa-Cqyb_uMP-4PkiQ8"
is_byok
false
latency
1140
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.011109
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
98.71%
Matches word count
n/a
neededClean
false
words
206
99.96%
Dialogue to Total Word Ratio
Ratio: 91.43%, Deviation: 1.43%
neededClean
false
wordsTotal
210
wordsDialogue
192
99.3354%