NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HJT5C7KYNYCVV91C3AFMW8
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
22.0s
Cost:
$0.027553
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9997%
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 deflates at three, Bill. That is our window," Molly whispered behind the hydrangea bush. "What about the clown?" "Giggles? Corrupt. I gave him twenty bucks and a balloon animal tutorial. He will stage a massive tantrum beside the juice boxes." "Brilliant. Then what?" "We breach the gift table, bag the Lego sets, and exfiltrate through the doggy door." "Molly, what if Leo spots us? He is six, but he bites like a feral badger," Bill muttered, squinting across the lawn. "Sour gummies. One handful to the left, and the birthday boy is totally neutralized." "And the mother?" "Uncle Gary will trap Brenda in a conversation about sourdough starter. She will be completely paralyzed." "You are a criminal genius. I saw three monster trucks out there." "Four, Bill. Plus an electric convertible." "How do we haul a convertible?" "You ride it, idiot. Put on the dinosaur mask and pretend you are hired entertainment." "The mask smells like wet ham," Bill sighed. "Suck it up. When the cake catches fire, grab the loot." "Are we stealing the goodie bags too?" "Obviously, Bill. We are professionals, not monsters. Check your walkie." "Ready on channel four." Molly zipped the duffel bag.
created_at
"2026-09-02T17:31:34.159Z"
9/2/2026, 5:31:34 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3974
moderation_latency
(null)
generation_time
21993
tokens_prompt
75
tokens_completion
1983
native_tokens_prompt
67
native_tokens_completion
7334
native_tokens_completion_images
0
native_tokens_reasoning
7036
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
0.02755275
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788370294-sR4gd64MVwhPbhLVCHus"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788370294-zn6LkbOvfyLcetDxXoZ3"
upstream_id
"dl2YaojGDfua9MoPnO-5oAE"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"dl2YaojGDfua9MoPnO-5oAE"
is_byok
false
latency
3973
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.02755275
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: 90.50%, Deviation: 0.50%
neededClean
false
wordsTotal
200
wordsDialogue
181
99.9997%