NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRD76TDW953GJRCDK0Z17K
Run Details
Model:
Gemini 3.7 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
29.9s
Cost:
$0.020949
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 binoculars, focusing past pastel streamers into the suburban backyard. Target zero was a mountainous pyramid of wrapped boxes glistening beneath the sun beside an oblivious clown twisting balloon poodles. It was undeniably the most perilous, high-stakes heist of their entire professional careers. "The inflatable castle provides optimal tactical cover," she whispered, sketching the perimeter on a greasy pizza napkin from their observation bush. Bill nervously adjusted his oversized teddy-bear costume. The humid polyester smelled faintly of stale corn chips and desperation. He tracked the patrol routes of thirty sugar-fueled toddlers currently weaponizing plastic kazoos near the sandbox. To an untrained eye, it was innocent chaos, but Bill recognized the raw kinetic violence of an unstoppable swarm. "Those juice-box addicts will tear us apart," Bill muttered, checking his stopwatch against the cake-cutting schedule. Molly rolled her eyes, slipping titanium pry bars into her pink utility belt. She had spent three weeks memorizing the backyard layout, calculating the weight distribution of boxed drones, and neutralizing the family labradoodle with gourmet sausages. Failure was completely out of the question for master thieves. "Just grab the mega Lego sets," she ordered, snapping her visor shut and gripping two empty burlap sacks.
created_at
"2026-09-03T13:48:02.871Z"
9/3/2026, 1:48:02 PM
model
"google/gemini-3.7-flash-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1405
moderation_latency
(null)
generation_time
17259
tokens_prompt
75
tokens_completion
1837
native_tokens_prompt
67
native_tokens_completion
5573
native_tokens_completion_images
0
native_tokens_reasoning
5320
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
0.020949
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443282-1AGBz8dbP81eXXGO27PD"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443282-CEP1EXpJ4cMJ5oNrv8N0"
upstream_id
"k3qZar-RA7WtjMcPidWQ4A0"
provider_responses
0
endpoint_id
"dd072012-3274-417d-97e3-e290cba37e31"
id
"k3qZar-RA7WtjMcPidWQ4A0"
is_byok
false
latency
1405
model_permaslug
"google/gemini-3.7-flash-20260813"
provider_name
"Google AI Studio"
status
200
total_cost
0.020949
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
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.24%, Deviation: 0.24%
neededClean
false
wordsTotal
205
wordsDialogue
21
100.0000%