NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HJ20ZB97CS5QSV9PMP179C
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
24.0s
Cost:
$0.033324
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 bulky goggles, an accessory entirely unnecessary under the glaring two o'clock afternoon sun. Across the manicured lawn of number forty, a pack of shrieking children circled a banquet table groaning under mountains of brightly wrapped boxes. It was an absolute goldmine of premium building bricks, expensive quadcopters, and padded cards stuffed with cash from wealthy grandparents. Molly unrolled a detailed architectural map across the warm hood of their battered getaway hatchback. She circled the wooden patio deck with red grease pencil. "The inflatable bounce castle covers the patio doors," Molly whispered. Bill peered through a pair of cheap binoculars, chewing nervously on stale strawberry licorice. A lanky performer wearing oversized checkered trousers was busily twisting balloon animals right beside their planned extraction route. "What about the birthday clown?" Bill asked. Molly flashed a smug grin, tapping an empty glass dropper against her tactical clipboard. "I spiked his seltzer with liquid melatonin," she said. Bill nodded in deep, solemn professional admiration. He hoisted two enormous velvet sacks onto his broad shoulders, fully preparing for the boldest breach of their criminal careers. Success depended on speed, stealth, and outmaneuvering thirty tiny monsters currently completely blitzed on blue raspberry cupcakes.
created_at
"2026-09-02T17:18:23.223Z"
9/2/2026, 5:18:23 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1373
moderation_latency
(null)
generation_time
23917
tokens_prompt
75
tokens_completion
2279
native_tokens_prompt
67
native_tokens_completion
8873
native_tokens_completion_images
0
native_tokens_reasoning
8618
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
0.033324
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788369503-wkD33CZ1jHKWbWy0FtQJ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788369503-Uvc0ywdHK0Vs7hBdgg2w"
upstream_id
"X1qYaqmlEpG7jrEP5aCD-Q8"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"X1qYaqmlEpG7jrEP5aCD-Q8"
is_byok
false
latency
1373
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.033324
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%