NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HJHZDK58CJ1P828J808APF
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
16.4s
Cost:
$0.021204
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, focusing on the suburban fortress currently swarming with hyperactive children. Plastic pinwheels spun violently along the perimeter fence, signaling hazardous wind conditions for their stealth approach. Inside the surveillance van, blueprints drawn in scented glitter marker lay spread across Molly’s knees. She tapped the primary objective, an ornate gift table groaning under mountains of neon wrapping paper. Molly loaded her confetti launcher despite the blinding midday sun. "The bouncy castle creates blind spots. Grab the Lego; I will secure the envelopes." Bill sighed, nervously eyeing the squeaking red foam noses resting on the dashboard. "Must we wear the clown wigs?" Molly glared at him with lethal professional intensity. Amateurs compromised operations, whereas true masterminds embraced synthetic rainbow afros. A territorial golden retriever patrolled the patio, but Molly had already neutralized that beast with gourmet cocktail sausages. The birthday boy was utterly mesmerized by a mediocre magician failing to extract plastic doves from an umbrella. It was the supreme tactical diversion. Decadent strawberry cupcakes sat unguarded beside dozens of pastel parcels containing remote control drones and unopened video games. Neither the screaming children nor their thoroughly exhausted parents stood a chance against suburban history’s greatest heist duo.
created_at
"2026-09-02T17:27:05.918Z"
9/2/2026, 5:27:05 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1609
moderation_latency
(null)
generation_time
16387
tokens_prompt
75
tokens_completion
1707
native_tokens_prompt
67
native_tokens_completion
5641
native_tokens_completion_images
0
native_tokens_reasoning
5392
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
0.021204
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788370025-ig3xoDGOqczqxljyV02c"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788370025-To6Vwnm4L8sHI7XXGwU9"
upstream_id
"alyYavEKx-b-4w_F06mgDQ"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"alyYavEKx-b-4w_F06mgDQ"
is_byok
false
latency
1608
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.021204
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%