NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KR8VJPD0FPP4T14TYHEX42
Run Details
Model:
Gemini 3.7 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
56.8s
Cost:
$0.014990
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 beneath the brim of an oversized party hat, unfurling a crayon blueprint across the hot hood of their dented getaway van. Outside, suburban chaos reigned supreme. Sugar crazed toddlers galloped across the manicured lawn like wild hyenas, their shrieks piercing the warm afternoon air while a harried father struggled to light sparklers. Behind them sat the mother lode: a towering mountain of glossy wrapping paper, oversized ribbons, and unopened electronic toys piled high on the patio table. Bill nervously wiped sweat from his mustache, clutching a velvet sack originally meant for diamonds, now repurposed for remote controlled plastic racecars and plush dinosaurs. He checked his stopwatch with trembling fingers, eyeing the colorful inflatable fortress oscillating rhythmically beside the wooden fence. "The bouncy castle is our primary extraction point," Molly whispered, tracing a bold line through the sandbox. "What about the glitter bomb traps?" Bill squeaked. "Wear goggles and secure the Lego," Molly ordered. She snapped her bubblegum, tossing him an industrial crowbar and two shiny festive party blowers. With ruthless military precision, the desperate duo synchronized their plastic digital watches, utterly determined to conquer the stickiest, highest stakes domestic heist of their entire bumbling criminal careers.
created_at
"2026-09-03T13:46:12.523Z"
9/3/2026, 1:46:12 PM
model
"google/gemini-3.7-flash-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1287
moderation_latency
(null)
generation_time
11596
tokens_prompt
75
tokens_completion
1193
native_tokens_prompt
67
native_tokens_completion
3984
native_tokens_completion_images
0
native_tokens_reasoning
3728
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
0.01499025
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443172-Yv00EYJHS8XT4JbBjWIt"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443172-tn5axETwyqjgMldkJkgc"
upstream_id
"JHqZavzaKbaW-8YPi9no0A0"
provider_responses
0
endpoint_id
"dd072012-3274-417d-97e3-e290cba37e31"
id
"JHqZavzaKbaW-8YPi9no0A0"
is_byok
false
latency
1287
model_permaslug
"google/gemini-3.7-flash-20260813"
provider_name
"Google AI Studio"
status
200
total_cost
0.01499025
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: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%