NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4V1WN15BG32CEA0K1GNNEVT
Run Details
Model:
Gemini 4 Argon (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.4s
Cost:
$0.003354
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
99.96%
Dialogue to Total Word Ratio
(details)
99.9411%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 a stained blueprint across the hood of their rusted van. "Listen, Bill. The target is little Timmy’s sixth birthday. Security is tight. We’re looking at twelve sugared-up ankle-biters, a sleep-deprived mother, and a rogue bounce house." Bill adjusted his ski mask. "What about the clown? I hate clowns. They have unpredictable aggro." "Bobo is on our side," Molly whispered. "I bribed him with a carton of Menthols. At 1400 hours, he makes a balloon giraffe so phallic it draws the parents' attention. That’s our window. We breach the patio." "And the loot?" "Stacked by the dining room credenza. Intel says Timmy’s grandpa bought him the limited-edition Millennium Falcon Lego set. Eight hundred bucks on the secondary market, easy. Plus, envelopes of crisp grandparent cash." "Sweet mother of pearl," Bill breathed. "What’s our disguise? Caterers?" "Better. I got us a two-person horse costume." "I am not being the butt again, Molly! Last time you ate tacos before the job!" "Focus! You’re the butt because you don't have the tactical vision to be the head. Grab the tranquilizer darts. If the pinata guard gets jumpy, we take him down." Bill sighed. "For the Legos." "For the Legos."
created_at
"2026-10-13T16:35:19.739Z"
10/13/2026, 4:35:19 PM
model
"google/gemini-4-argon-20261013"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1085
moderation_latency
(null)
generation_time
5366
tokens_prompt
75
tokens_completion
314
native_tokens_prompt
97
native_tokens_completion
316
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
0.003354
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791909319-7SZH5ifJYZUyvEFnjWGq"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791909319-y3l5DNWgzCEbDAJdDEbC"
upstream_id
"x13OapHCMcXUjMcP-fzn4QQ"
provider_responses
0
endpoint_id
"4934736c-d662-4fe3-98eb-56def8c8c174"
id
"x13OapHCMcXUjMcP-fzn4QQ"
is_byok
false
latency
1085
model_permaslug
"google/gemini-4-argon-20261013"
provider_name
"Google AI Studio"
status
200
total_cost
0.003354
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
99.92%
Matches word count
n/a
neededClean
false
words
197
99.96%
Dialogue to Total Word Ratio
Ratio: 88.61%, Deviation: 1.39%
neededClean
false
wordsTotal
202
wordsDialogue
179
99.9411%