NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4V1R4F1XFYNJEVSJXP3K7MY
Run Details
Model:
Gemini 4 Argon (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6.3s
Cost:
$0.003114
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
72.29%
Dialogue to Total Word Ratio
(details)
84.1399%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 hand-drawn blueprint across the hood of their rusted sedan, weighing down the corners with stale donuts. She tapped a red crayon mark near the backyard patio, her eyes gleaming with misplaced ambition. "The target is little Timmy's seventh birthday," Molly whispered fiercely. "Intel says the gift table is overflowing with high-end plastic." Bill adjusted his tight fabric mask, looking nervously toward the brightly decorated suburban house. A giant pink inflatable unicorn bobbed menacingly over the wooden fence. "I don't know about this, Molly," Bill muttered, sweating through his striped shirt. "Six-year-olds are vicious when hopped up on cake." Molly scoffed, jamming a plastic water pistol into her leather holster. She grabbed a hefty burlap sack and tossed it directly into Bill's trembling arms. "We go in during the piƱata distraction," she explained, pointing at the crayon drawing. "While the tiny savages fight over dropped candy, we bag the rectangular boxes. Those are definitely the expensive building sets. In and out, five minutes tops." Bill sighed, hoisting the empty sack over his slouched shoulder. "If I get bitten by a toddler again, I'm taking seventy percent of the Lego profits," Bill warned her. "Deal," Molly grinned, racking her squirt gun. "Now put on your clown nose."
created_at
"2026-10-13T16:32:51.692Z"
10/13/2026, 4:32:51 PM
model
"google/gemini-4-argon-20261013"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1701
moderation_latency
(null)
generation_time
6308
tokens_prompt
75
tokens_completion
339
native_tokens_prompt
97
native_tokens_completion
292
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
0.003114
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791909171-426X0xRbm3st0tN7bd0M"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791909171-qqIMmGCghROmMLRANvsJ"
upstream_id
"M13OapSAL4iv1MkP5_vZwQw"
provider_responses
0
endpoint_id
"4934736c-d662-4fe3-98eb-56def8c8c174"
id
"M13OapSAL4iv1MkP5_vZwQw"
is_byok
false
latency
1695
model_permaslug
"google/gemini-4-argon-20261013"
provider_name
"Google AI Studio"
status
200
total_cost
0.003114
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
95.99%
Matches word count
n/a
neededClean
false
words
208
72.29%
Dialogue to Total Word Ratio
Ratio: 42.45%, Deviation: 7.55%
neededClean
false
wordsTotal
212
wordsDialogue
90
84.1399%