NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-19-01M7SP7EH460EMT5VWSD22XHRN
Run Details
Model:
Gemini 4 Neon (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
20.3s
Cost:
$0.033096
Provider:
Google
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9997%
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 hand-drawn blueprint across the sticky diner booth, weighing down the corners with salt shakers and a half-eaten basket of fries. The target was a suburban backyard on Elm Street, currently fortified by a rented bouncy castle and a perimeter of folding chairs. Bill adjusted his oversized sunglasses, squinting at the crayon-rendered layout of the gift table. He tapped a grease-stained finger against the designated clown zone, his expression grimly professional. "We hit the bouncy castle first, cause a distraction, then grab the Lego sets," Molly whispered. Bill frowned, stroking his chin as he calculated the risks of navigating thirty sugar-fueled seven-year-olds. The logistics were a nightmare. There would be sticky fingers everywhere, unpredictable trajectories of stray balloons, and a high probability of encountering a hyper-vigilant PTA mother guarding the juice boxes. Still, the payout was undeniable. Rumor had it that little Timmy's uncle worked at a high-end electronics store, meaning a brand-new gaming console was sitting beneath a mountain of brightly colored wrapping paper. "What about the terrifying balloon magician?" Bill asked. Molly smiled, her eyes gleaming with manic ambition as she pulled two cheap party hats from her duffel bag. They were definitely going in undercover.
created_at
"2026-11-19T10:39:21.645Z"
11/19/2026, 10:39:21 AM
model
"google/gemini-4-neon-20261118"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2726
moderation_latency
(null)
generation_time
20275
tokens_prompt
75
tokens_completion
745
native_tokens_prompt
97
native_tokens_completion
2187
native_tokens_completion_images
0
native_tokens_reasoning
1921
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
0.033096
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1795084761-FMy2wwYIo34Qdbv6mnrG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1795084761-ETQy3WfOmOTepO84sZFM"
upstream_id
"2dH-aqHBKtWbpucPhuTswQ8"
provider_responses
0
endpoint_id
"cbc1d01f-e431-41ec-9abb-36c1a5b10cb4"
id
"2dH-aqHBKtWbpucPhuTswQ8"
is_byok
false
latency
2726
model_permaslug
"google/gemini-4-neon-20261118"
provider_name
"Google"
status
200
total_cost
0.033096
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
100.00%
Dialogue to Total Word Ratio
Ratio: 9.52%, Deviation: 0.48%
neededClean
false
wordsTotal
210
wordsDialogue
20
99.9997%