NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCXKT699C885GNE16EB0HGS
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
27.0s
Cost:
$0.053433
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
Molly adjusted her tactical goggles, though it was bright daylight inside the suburban garage. Spread across the hood of their dented hatchback were detailed blueprints of a big residential house, annotated with red ink pointing out lethal security hazards like loose Lego bricks and angry mothers. Bill nervously adjusted his turtleneck, sweating profusely under the weight of three oversized burlap sacks tucked beneath his belt. Stealing wrapped packages from a group of hyperactive children was high risk and high reward, especially considering the rumor that young Timmy’s grandmother had brought a shiny motorized toy car. "The bouncy castle is our primary extraction zone," Molly declared, tapping a plastic magnifying glass against a pastel invitation card. Bill shuddered, checking his watch. "I naturally despise apple juice." "Focus, Bill. Timmy turns seven at noon," she warned, adjusting a fake clown nose that concealed her mini radio. Bill swallowed hard, nervously gripping his glittery smoke bomb. The wall clock ticked rhythmically closer to twelve. Soon, sugary birthday cake would be served, uncontrollable sugar crashes would inevitably begin, and thirty pristine wrapped gifts would finally be theirs for the taking without a single crying child noticing their clever grand escape from this suburban backyard.
created_at
"2026-07-25T15:17:02.804Z"
7/25/2026, 3:17:02 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1948
moderation_latency
(null)
generation_time
26951
tokens_prompt
75
tokens_completion
1931
native_tokens_prompt
67
native_tokens_completion
7111
native_tokens_completion_images
0
native_tokens_reasoning
6867
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
0.053433
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"b9NkavqzHNeGjrEPmNmZ0Ak"
is_byok
false
latency
1948
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-1784992622-tKlIM4VFoiCjBbUQjdDY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784992622-xOwAtH01U4ikvzTZoGkj"
upstream_id
"b9NkavqzHNeGjrEPmNmZ0Ak"
total_cost
0.053433
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
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%