NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4V1YHWC1NW7Q4JFP1QJNB17
Run Details
Model:
Gemini 4 Argon (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
33.9s
Cost:
$0.036674
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 kitchen table, weighing down the corners with brass knuckles and a stale toaster strudel. It was the layout of the community center. Bill leaned in, adjusting his tactical turtleneck, sweating profusely beneath the flickering kitchen bulb. He tapped a greasy finger on the designated loot zone, located directly beside the bouncy castle. The target was Timmy Henderson’s seventh birthday bash. Intelligence suggested the kid’s wealthy, divorced parents were aggressively overcompensating with rare Lego sets and crisp, untraceable twenty dollar bills tucked inside musical greeting cards. It was the score of the century, provided they could bypass the erratic patrol patterns of thirty hyperactive toddlers and a caffeinated soccer mom guarding the gift table. Molly traced the escape route with a stolen purple crayon. They had a narrow four minute window between the pinata bashing and the ceremonial lighting of the candles. "And what about the clown?" Bill whispered, his voice trembling. "I packed the tranquilizer darts, didn't I?" Molly snapped, racking the plastic slide of a modified Nerf blaster. "Nobody makes a balloon giraffe on my watch." Bill nodded grimly, smearing blue frosting across his cheekbones like commando war paint, ready for action.
created_at
"2026-10-13T16:36:22.04Z"
10/13/2026, 4:36:22 PM
model
"google/gemini-4-argon-20261013"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2394
moderation_latency
(null)
generation_time
33886
tokens_prompt
75
tokens_completion
1218
native_tokens_prompt
97
native_tokens_completion
3648
native_tokens_completion_images
0
native_tokens_reasoning
3388
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
0.036674
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791909382-4YBYHevUuO78O8evZqLG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791909382-iaKnH5kNqU2c4pWmt0oq"
upstream_id
"Bl7OarqCCeKWjMcP-PuR2Qs"
provider_responses
0
endpoint_id
"4934736c-d662-4fe3-98eb-56def8c8c174"
id
"Bl7OarqCCeKWjMcP-PuR2Qs"
is_byok
false
latency
2394
model_permaslug
"google/gemini-4-argon-20261013"
provider_name
"Google AI Studio"
status
200
total_cost
0.036674
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%