NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-20-01KS25V9M963J3S0STGRRYE33P
Run Details
Model:
Gemini 3.5 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.8s
Cost:
$0.002252
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
40.0831%
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
The velvet curtain of the bounce house ruffled as Molly adjusted her plastic binoculars. Through the mesh viewing window of their inflatable camouflage base, she surveyed the target zone: a suburban backyard swarming with sugar-crazed eight-year-olds. At the center of the lawn stood the holy grail, a folding table groaning under the weight of brightly wrapped boxes, towering gift bags, and one suspiciously heavy parcel shaped like an electric dirt bike. She turned to her partner. Bill was currently struggling to squeeze his broad shoulders into a lime-green dinosaur costume, his face flushed red beneath the plush triceratops hood. He choked on a stray piece of synthetic purple felt. We go in during the pinata distraction, Molly whispered, her fingers tracing the perimeter map she had drawn in ketchup on a paper plate. Bill grunted, fiercely tugging at his dinosaur tail. This tail is ruining my center of gravity, he muttered. Molly ignored his wardrobe malfunction, sliding a disguised grab-and-go sack disguised as a giant balloon animal pump across the vinyl floor. Once the papier-mache donkey bursts, she said, we sweep the table.
created_at
"2026-05-20T07:50:48.725Z"
5/20/2026, 7:50:48 AM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
766
moderation_latency
(null)
generation_time
2708
tokens_prompt
77
tokens_completion
295
native_tokens_prompt
67
native_tokens_completion
239
native_tokens_completion_images
0
native_tokens_reasoning
0
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
"standard"
usage
0.0022515
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"2GcNape9NuSs1MkPs-mymAw"
is_byok
false
latency
766
model_permaslug
"google/gemini-3.5-flash-20260519"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer
(null)
request_id
"req-1779263448-QIu9lU4quRJ9ZxCy8YAq"
session_id
(null)
api_type
"completions"
id
"gen-1779263448-ZnmcK34FfwuApBjsq3qr"
upstream_id
"2GcNape9NuSs1MkPs-mymAw"
total_cost
0.0022515
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
183
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
190
wordsDialogue
0
40.0831%