NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCVFC4ZSP0646TK35ZB6N56
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
13.2s
Cost:
$0.022211
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
65.09%
Dialogue to Total Word Ratio
(details)
82.5352%
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
"Did you secure the schematics?" Molly asked. "Got them right here," Bill whispered. "The bouncy castle covers our south approach, but we must avoid the toddlers. They're heavily sugared, totally feral, and extremely unpredictable." "Understood. What's the payload?" "Sixteen wrapped boxes, four gift bags, and a massive Lego set worth eighty bucks." "Jackpot. How's the perimeter defense?" "One sleepy golden retriever, a tired dad, and a mom distracted by pin-the-tail-on-the-donkey." "Perfect. I'll infiltrate through the back patio dressed as the entertainer." "You're going full clown?" "It's the only way, Bill. Balloon animals buy us critical time. Once I distract seven-year-old Timmy, you slip past the chocolate fountain and secure the loot." "What if your squeaky shoes give us away?" "They won't. Did you pack the smoke bombs?" "They're glitter bombs, Molly. It's a birthday." "Even better. Just make sure the getaway minivan is running." "The engine is idling, but what about the pinata? It's loaded with high-grade sour gummies." "Leave the candy, Bill! We're here for video games and cash envelopes from grandparents. Stay focused!" "Right, sorry. What's our extraction timeline?" "Three minutes max, right before the juice box rush." "Copy that. Let me grab my nose squeaker." "Let's steal some toys."
created_at
"2026-07-25T14:39:40.2Z"
7/25/2026, 2:39:40 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1412
moderation_latency
(null)
generation_time
13095
tokens_prompt
75
tokens_completion
1317
native_tokens_prompt
67
native_tokens_completion
2948
native_tokens_completion_images
0
native_tokens_reasoning
2606
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
0.0222105
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"rMpkaovuD-vR-8YPqISsqAo"
is_byok
false
latency
1412
model_permaslug
"google/gemini-3.6-flash-20260721"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784990380-gigCPWyW3zcvV9wcbCJ7"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784990380-RJrotzAViWuhFhESpEIc"
upstream_id
"rMpkaovuD-vR-8YPqISsqAo"
total_cost
0.0222105
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
65.09%
Dialogue to Total Word Ratio
Ratio: 98.10%, Deviation: 8.10%
neededClean
false
wordsTotal
210
wordsDialogue
206
82.5352%