NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCT2FM27XAXFKS2F11JKR5R
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
27.1s
Cost:
$0.055623
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
87.39%
Dialogue to Total Word Ratio
(details)
93.6948%
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 pack the smoke bombs?" Molly whispered softly. "Better. I brought glitter," Bill replied. "Kids hate glitter." "Kids love glitter, you idiot! We are robbing a seven-year-old's birthday party, not hitting a nightclub." "Fine. But my bouncy castle exit strategy is solid." "Bill, focus. The primary targets are the wrapped Lego sets and video games under the backyard gazebo, guarded by a clown named Bobo." "I can easily take Bobo." "Bobo is a decorated former Marine." "Wait, really?" "Yes. So, here is the master plan. You are going to create a major distraction using the apple juice boxes." "Should I spill the punch instead?" "No, throw them directly at the bouncy castle power strip. When that castle deflates, total chaos erupts. Parents panic. Toddlers cry. That is when I swipe all the presents." "Brilliant. What about the giant star piƱata?" "Leave it. It is full of organic raisins." "Savages. What is our backup route after grabbing the birthday loot?" "We sprint to the getaway minivan." "Is the booster seat installed?" "Obviously. We must blend in completely, Bill. Put on your pointy paper party hat and act natural." "I am ready," Bill said quietly. "Let's go ruin Little Timmy's big day."
created_at
"2026-07-25T14:15:09.195Z"
7/25/2026, 2:15:09 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1223
moderation_latency
(null)
generation_time
27039
tokens_prompt
75
tokens_completion
1804
native_tokens_prompt
67
native_tokens_completion
7403
native_tokens_completion_images
0
native_tokens_reasoning
7096
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
0.055623
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"7cRkauHmD92ijMcPtNWg8As"
is_byok
false
latency
1223
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-1784988909-TYs9cJ2LIKQsQrsTMW06"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784988909-ExEeY63rADqStyrFllQF"
upstream_id
"7cRkauHmD92ijMcPtNWg8As"
total_cost
0.055623
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
201
87.39%
Dialogue to Total Word Ratio
Ratio: 96.06%, Deviation: 6.06%
neededClean
false
wordsTotal
203
wordsDialogue
195
93.6948%