NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KR792N6PEHMZE9E2DZTHFA
Run Details
Model:
Gemini 3.7 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
15.0s
Cost:
$0.017042
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 slammed a crude blueprint onto the hood of their battered getaway van. It detailed the perilous terrain of suburban backyard security, complete with a fortified sandbox, an erratic golden retriever, and the target: little Timmy’s towering mountain of unopened birthday gifts. Bill adjusted his tactical goggles, which were entirely unnecessary in the blinding midday sun. He peered intently at the miniature plastic playground marked with bright red tape. The stakes were astronomical; dark neighborhood rumors suggested Timmy had secured the coveted legendary robot. "The bouncy castle is our extraction point," Molly whispered, pointing a sparkly glitter pen at the inflatable fortress. Bill nervously wiped sweat from his mustache with a silk pirate bandana, visibly agonizing over the dangerous layout. "What about the clown?" he asked. Molly narrowed her cold eyes and unclipped a small pouch from her black vest. "Pocket sand. He will not stop our grand heist," she promised grimly. Deeply satisfied with their ruthless contingency plan, Bill checked his waterproof digital watch. Cake consumption was scheduled for precisely fourteen hundred hours. When the epic toddler sugar rush reached critical chaotic mass, these two hardened criminals would strike swiftly, breach the wooden fence, and steal every wrapped toy.
created_at
"2026-09-03T13:44:35.881Z"
9/3/2026, 1:44:35 PM
model
"google/gemini-3.7-flash-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2317
moderation_latency
(null)
generation_time
14631
tokens_prompt
75
tokens_completion
1403
native_tokens_prompt
67
native_tokens_completion
4531
native_tokens_completion_images
0
native_tokens_reasoning
4284
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
0.0170415
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443075-xYVnZ8QZPZbDo0kWrOrL"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443075-y5Qi3UAMi4QCUIwqZVkJ"
upstream_id
"xHmZaqzhBsi4sOIPjI2f8Ao"
provider_responses
0
endpoint_id
"dd072012-3274-417d-97e3-e290cba37e31"
id
"xHmZaqzhBsi4sOIPjI2f8Ao"
is_byok
false
latency
2317
model_permaslug
"google/gemini-3.7-flash-20260813"
provider_name
"Google AI Studio"
status
200
total_cost
0.0170415
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%