NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HHM9S0P3Q12PRKQZ1EDTTT
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
18.0s
Cost:
$0.025498
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
Crouched beneath the prickly cover of Mrs. Gable's hydrangea bushes, Molly unfolded the master blueprint, hastily rendered on a stolen paper placemat with a purple crayon. Her black tactical turtleneck, while undeniably professional, offered zero protection against angry fire ants. Beside her, Bill nervously adjusted a pair of oversized novelty sunglasses that flashed bright neon pink whenever he blinked. Across the sunlit lawn, thirty hyperactive children waged total war with sticky glitter bombs and tropical juice boxes. It was a chaotic carnival of sugar madness, perfectly obscuring their true criminal objective: an enormous mountain of wrapped boxes piled beneath the patio pergola. Expensive video games, rare building blocks, and padded greeting cards from wealthy grandparents sat virtually unguarded. Molly checked her plastic digital watch. "The clown is handled, and the bouncy castle deflates at noon precisely." Bill smirked, checking his reinforced burlap sack and cracking his knuckles with quiet theatrical flair. He had spent three sleepless weeks studying toddler behavioral psychology for this singular operation. "Good, strike the loot table during musical chairs." Molly nodded gravely in agreement. It was the ultimate suburban heist. Soon, forty kindergartners would weep bitter tears into their sweet cupcakes. Victory tasted like vanilla frosting.
created_at
"2026-09-02T17:10:53.482Z"
9/2/2026, 5:10:53 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1462
moderation_latency
(null)
generation_time
18014
tokens_prompt
75
tokens_completion
1886
native_tokens_prompt
67
native_tokens_completion
6786
native_tokens_completion_images
0
native_tokens_reasoning
6535
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
0.02549775
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788369053-IPuCihEoMiFyv4iZeLlY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788369053-LtaUEYGtM8xDyH0jA3F9"
upstream_id
"nViYapjAIcfn_uMPzaCWoQ0"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"nViYapjAIcfn_uMPzaCWoQ0"
is_byok
false
latency
1462
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.02549775
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%