NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-19-01M7SP5JC6S4T9BMXNV6X4SHS8
Run Details
Model:
Gemini 4 Neon (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
22.8s
Cost:
$0.041616
Provider:
Google
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
97.95%
Dialogue to Total Word Ratio
(details)
98.9756%
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 slapped a glossy brochure for Chuckles’ Party Barn onto the stained kitchen table. She adjusted her black turtleneck with the gravity of a general plotting an invasion. Across from her, Bill squinted at a hand-drawn map of the Henderson backyard, his fingers dusted with orange cheese powder. Their target was unprecedented: little Timmy Henderson’s seventh birthday extravaganza. Rumor had it the kid’s billionaire grandfather was attending, meaning the wrapping paper hid high-end electronics and vintage collectibles. Molly tapped a red marker against a crudely sketched inflatable fortress. "The bouncy castle is our blind spot. We hit the gift table right during cake." Bill nervously chewed on a pretzel stick, his eyes darting to the perimeter defenses noted in the margins. A hired magician, three caffeinated soccer moms, and a hyperactive golden retriever stood between them and early retirement. He swallowed hard, picturing the inevitable chaos of sugar-fueled toddlers blocking their escape route. "What about the terrifying clown?" Molly smiled coldly, pulling two brightly colored balloon animals, a squeaky red nose, and a pair of oversized plastic sunglasses from her black duffel bag. Tonight, they weren't just thieves. They were the entertainment, and they were taking every single wrapped gift.
created_at
"2026-11-19T10:38:20.052Z"
11/19/2026, 10:38:20 AM
model
"google/gemini-4-neon-20261118"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2445
moderation_latency
(null)
generation_time
22804
tokens_prompt
75
tokens_completion
911
native_tokens_prompt
97
native_tokens_completion
2755
native_tokens_completion_images
0
native_tokens_reasoning
2492
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
"default"
usage
0.041616
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1795084700-0HOM0Ggprss4pHt5bNQw"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1795084700-AWOahECKpGAh1MCVqmEP"
upstream_id
"nNH-ap3YBvSR9LsP1eXW8Ac"
provider_responses
0
endpoint_id
"cbc1d01f-e431-41ec-9abb-36c1a5b10cb4"
id
"nNH-ap3YBvSR9LsP1eXW8Ac"
is_byok
false
latency
2444
model_permaslug
"google/gemini-4-neon-20261118"
provider_name
"Google"
status
200
total_cost
0.041616
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google"
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
97.95%
Dialogue to Total Word Ratio
Ratio: 13.79%, Deviation: 3.79%
neededClean
false
wordsTotal
203
wordsDialogue
28
98.9756%