NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4V1SK22H77NVZEC2R8Q5M3R
Run Details
Model:
Gemini 4 Argon (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.7s
Cost:
$0.002924
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
99.81%
Dialogue to Total Word Ratio
(details)
99.2628%
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 spread the blueprint of Barnaby’s Bounce-A-Rama across the sticky diner table, weighting the corners down with a ketchup bottle and a stolen tiara. Across from her, Bill aggressively chewed a toothpick, his brow furrowed in deep, professional concentration as he studied the brightly colored layout. This was their magnum opus. Little Lord Preston’s seventh birthday bash was tomorrow, and the guest list read like a billionaire’s tax bracket. The loot table would be overflowing with high-end electronics, envelopes of crisp cash, and limited-edition plastic bricks that fetched a fortune on the dark web. Molly tapped the schematic with a fingernail painted jet black. They needed to bypass the toddler ball pit, neutralize the face-painting station, and slip past sixty sugar-crazed youths. A single stray balloon animal could trigger total chaos. "We crawl through the inflatable castle," Molly whispered. Bill frowned, rubbing his chin. "What about the clown?" "Tranquilizer dart to the juggle-balls," she replied smoothly. Bill nodded slowly, respecting the ruthless tactical genius of the plan. He zipped up his leather jacket, mentally preparing himself for the sensory hellscape of screaming first-graders and animatronic pizza bears. Tomorrow, they would finally retire like kings.
created_at
"2026-10-13T16:33:39.406Z"
10/13/2026, 4:33:39 PM
model
"google/gemini-4-argon-20261013"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1099
moderation_latency
(null)
generation_time
5638
tokens_prompt
75
tokens_completion
332
native_tokens_prompt
97
native_tokens_completion
273
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
(null)
usage
0.002924
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791909219-HT6kb1Iof5B8VuDVJJmk"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791909219-w2opZm4hiCoLM0iOafZT"
upstream_id
"Y13OaozRHfrQjMcPx4SzqAI"
provider_responses
0
endpoint_id
"4934736c-d662-4fe3-98eb-56def8c8c174"
id
"Y13OaozRHfrQjMcPx4SzqAI"
is_byok
false
latency
1098
model_permaslug
"google/gemini-4-argon-20261013"
provider_name
"Google AI Studio"
status
200
total_cost
0.002924
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
98.71%
Matches word count
n/a
neededClean
false
words
194
99.81%
Dialogue to Total Word Ratio
Ratio: 7.92%, Deviation: 2.08%
neededClean
false
wordsTotal
202
wordsDialogue
16
99.2628%