NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCT5G406B2QZJTBYTP36W4X
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
34.4s
Cost:
$0.069325
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 unrolled the blueprint of the suburban backyard onto the kitchen counter. It was a perilous zone of sticky glitter, spilled juice pouches, and unbridled toddler chaos. On the kitchen island lay their specialized heist gear: stealthy velcro sneakers, dark sunglasses, and three oversized burlap sacks clearly labeled NOT PRESENTS. Bill nervously adjusted his tactical party hat, the tight elastic chin strap pinching his cheeks. Outside, twenty hyperactive seven-year-olds were currently distracted by a piƱata shaped like a glittery unicorn. This was their narrow window of opportunity. The mother was busy pouring pink lemonade, while the father was trapped in an escalating foam-sword duel near the dirty sandbox. Molly anxiously checked her tactical plastic watch. Cake time approached, promising total pandemonium. "Did you manage to bypass the vicious toddler security guards?" Molly whispered. "I bribed the birthday boy with ten cold juice boxes," Bill replied. Molly nodded solemnly, pulling down her night-vision goggles despite the blinding afternoon sun. The glorious mountain of brightly wrapped gifts sitting directly on the wooden patio table called to them like a sweet siren song. Legos, remote-controlled cars, and mysterious heavy packages were waiting to be liberated before the terrible sugar rush officially began today.
created_at
"2026-07-25T14:16:48.01Z"
7/25/2026, 2:16:48 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1210
moderation_latency
(null)
generation_time
34307
tokens_prompt
75
tokens_completion
2851
native_tokens_prompt
67
native_tokens_completion
9230
native_tokens_completion_images
0
native_tokens_reasoning
8969
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
0.0693255
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"UMVkaoXUA4LGjMcP1-XhsQ0"
is_byok
false
latency
1210
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-1784989008-3FeV4MelJmbjCZM4xew0"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784989008-wkr1PRu2JTPwS4yRWIvF"
upstream_id
"UMVkaoXUA4LGjMcP1-XhsQ0"
total_cost
0.0693255
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: 9.76%, Deviation: 0.24%
neededClean
false
wordsTotal
205
wordsDialogue
20
100.0000%