NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCTDDR3NA4T1M6CCCAFGRAD
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
24.6s
Cost:
$0.043398
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
96.08%
Dialogue to Total Word Ratio
(details)
98.0386%
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
"We strike at high noon," Molly whispered nervously. "Lunchtime?" Bill asked. "They will be eating ice cream and cake!" "Precisely. Sugar coma. The wild kids will not even know what hit them." "What about the terrifying bouncy castle guards lurking by the slide?" "I will deploy juice boxes to distract the hyper toddlers," she said quickly. "You grab the shiny wrapped loot." "Is Timmy’s giant LEGO starship our primary target?" "Yes, but do not ignore that sparkly pink pony package. That is pure playground gold." "Got it. What is our secret exfiltration route out?" "Through the tiny rear kitchen doggy door." "Molly, I am over six feet tall!" "Then squeeze, Bill! Squeeze hard for the glory!" "What if the creepy hired birthday clown spots us?" "Honk his red nose and run like hell. Do you have our tactical disguise ready?" "I brought oversized clown shoes and a ridiculous rainbow wig," he muttered unhappily. "Brilliant. We sneak inside, swap the huge gift pile with empty cardboard boxes, and vanish into the wooden sandbox." "Those spoiled kids will not realize they got totally robbed until mandatory afternoon naptime." "Synchronize our watches, partner. Operation Birthday Blitz is officially a go right now."
created_at
"2026-07-25T14:21:07.727Z"
7/25/2026, 2:21:07 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1419
moderation_latency
(null)
generation_time
24534
tokens_prompt
75
tokens_completion
1788
native_tokens_prompt
67
native_tokens_completion
5773
native_tokens_completion_images
0
native_tokens_reasoning
5486
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
0.043398
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"U8ZkaqH9MaHVjMcPmdS76Qs"
is_byok
false
latency
1419
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-1784989267-UAAzGJRUnL0xa7QUCgYc"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784989267-xryqzxQ3HnmPtgq9dbve"
upstream_id
"U8ZkaqH9MaHVjMcPmdS76Qs"
total_cost
0.043398
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
199
96.08%
Dialogue to Total Word Ratio
Ratio: 94.47%, Deviation: 4.47%
neededClean
false
wordsTotal
199
wordsDialogue
188
98.0386%