NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4V2380JBW3YRSE80MDX3AAH
Run Details
Model:
Gemini 4 Argon (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
19.5s
Cost:
$0.022704
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 unrolled the blueprints across the sticky diner booth, weighing down the corners with salt shakers and a half-eaten cruller. It was a fortress of suburban affluence: the Henderson backyard. She tapped a red Sharpie against a crudely drawn octagon labeled the Bouncy Castle. Bill squinted through his thick spectacles, his scarred knuckles white around a mug of decaf. For thirty years, they had cracked Swiss vaults and lifted priceless diamonds from Parisian museums. Now, inflation and poor crypto investments had reduced them to hitting little Timmy Henderson’s seventh birthday bash. The target was a folding table near the patio, reportedly buckling under the weight of high-end Lego sets and envelopes stuffed with crisp twenty-dollar bills from competitive grandmas. Molly slid a surveillance photo across the laminate. It showed a heavily painted man twisting a poodle out of latex. "Watch out for the clown. He packs heat," Molly whispered, her voice gravelly from decades of smoking. Bill shuddered, adjusting his ski mask. "Squirt gun or balloon animals?" "Both. God help us. Wear the goggles." Bill nodded grimly, synchronizing his novelty SpongeBob watch. At precisely two-thirty, during the piñata distraction, they would strike. No mercy, no prisoners, and definitely no cake.
created_at
"2026-10-13T16:38:55.779Z"
10/13/2026, 4:38:55 PM
model
"google/gemini-4-argon-20261013"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2329
moderation_latency
(null)
generation_time
19440
tokens_prompt
75
tokens_completion
916
native_tokens_prompt
97
native_tokens_completion
2251
native_tokens_completion_images
0
native_tokens_reasoning
1978
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
(null)
usage
0.022704
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791909535-PqQl3cQ2e9aAjF7cdnCY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791909535-sXGIYE1mc7KzxcpsLPyn"
upstream_id
"n17OapPRN8zQ-8YPooGXqA4"
provider_responses
0
endpoint_id
"4934736c-d662-4fe3-98eb-56def8c8c174"
id
"n17OapPRN8zQ-8YPooGXqA4"
is_byok
false
latency
2329
model_permaslug
"google/gemini-4-argon-20261013"
provider_name
"Google AI Studio"
status
200
total_cost
0.022704
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: 9.80%, Deviation: 0.20%
neededClean
false
wordsTotal
204
wordsDialogue
20
100.0000%