NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRTWGXGV3A9Z4K3MG2W6XS
Run Details
Model:
Gemini 3.7 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.5s
Cost:
$0.013756
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
75.48%
Dialogue to Total Word Ratio
(details)
59.4298%
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 our tactical getaway transport?" Molly asked. "I upgraded us to a tandem bicycle with sparkly pink streamers," Bill said proudly. "Bill, we are elite masterminds hitting Timmy's eighth birthday, not a circus." "Streamers provide suburban camouflage! Now, what is our primary entry vector?" "The bouncy castle. We breach the rear air exhaust tube at precisely fourteen hundred hours, right when the terrible clown distracts the oblivious parents with balloon dachshunds." "Brilliant. That hack's pathetic balloon routine will cause total chaos. Where is the motherlode located?" "The dining room table. Reconnaissance confirms four expensive Lego sets, a remote-controlled racing drone, and an exceptionally thick envelope from Grandma." "Grandma envelopes are pure, untraceable cash. What about the homeowner's vicious perimeter security?" "A chubby golden retriever puppy. I packed half a pound of artisanal smoked bacon." "You ruthless genius. What is our fast exfiltration route?" "Down the plastic spiral slide, across the sandbox, over the cedar fence, and straight onto the bicycle." "Synchronize party watches, Molly. It is finally showtime." "Strap on your festive cone hat, Bill. Let's go rob this birthday blind."
created_at
"2026-09-03T13:55:18.178Z"
9/3/2026, 1:55:18 PM
model
"google/gemini-3.7-flash-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1091
moderation_latency
(null)
generation_time
11406
tokens_prompt
75
tokens_completion
1265
native_tokens_prompt
67
native_tokens_completion
3655
native_tokens_completion_images
0
native_tokens_reasoning
3383
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
0.0137565
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443718-S02PzGoDlvkQigrBf4J2"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443718-ppIC5l0O2JSGWC06uKFl"
upstream_id
"RnyZau2UFLCqsOIPhLiU2A8"
provider_responses
0
endpoint_id
"dd072012-3274-417d-97e3-e290cba37e31"
id
"RnyZau2UFLCqsOIPhLiU2A8"
is_byok
false
latency
1091
model_permaslug
"google/gemini-3.7-flash-20260813"
provider_name
"Google AI Studio"
status
200
total_cost
0.0137565
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
183
75.48%
Dialogue to Total Word Ratio
Ratio: 97.28%, Deviation: 7.28%
neededClean
false
wordsTotal
184
wordsDialogue
179
59.4298%