NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-19-01M7SVCKHJBQN8GFHY0C4XHWV9
Run Details
Model:
Gemini 4 Hydrogen (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.7s
Cost:
$0.012911
Provider:
Google
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
65.86%
Dialogue to Total Word Ratio
(details)
82.9203%
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
"Okay, walk me through the perimeter again," Molly said. "It's a bouncy castle, Molly, not Fort Knox," Bill sighed. "There's a six-foot fence, a golden retriever, and a clown." "What kind of clown?" "A sad one. He's smoking behind the shed." "Good. Disgruntled staff is our way in. What about the loot?" "Presents are stacked on the picnic table next to the juice boxes. Mostly Lego sets, some Barbie dreamhouses, and I'm pretty sure I saw a PlayStation box." "A PlayStation? For an eight-year-old's birthday?" "Rich neighborhood. The kid's name is Tarquin." "Of course it is. How do we handle the security?" "The golden retriever? I brought bacon." "No, the mothers. They're vicious when their Chardonnay gets warm." "I've got a decoy. I'll release a stray hamster near the buffet." "Genius. And the getaway?" "My cousin's ice cream truck. We blend right in, grab the gifts, and—" "Wait. Do we have to sell ice cream?" "Only if they have exact change." "Bill, you're a mastermind." "I know. Now put on the balloon-animal apron. We move at naptime." "Eight-year-olds don't take naps, Bill." "They do after three liters of fruit punch and a sugar crash. Trust the process, Molly."
created_at
"2026-11-19T12:09:33.5Z"
11/19/2026, 12:09:33 PM
model
"google/gemini-4-hydrogen-20261112"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1715
moderation_latency
(null)
generation_time
11679
tokens_prompt
75
tokens_completion
613
native_tokens_prompt
97
native_tokens_completion
1702
native_tokens_completion_images
0
native_tokens_reasoning
1364
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
0.0129105
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1795090173-VqziFZysAwxGGxYo0uQa"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1795090173-ZQNAD3y9iSDnXVq2qmC7"
upstream_id
"_eb-arGgIuaaotQP4b7_6Ac"
provider_responses
0
endpoint_id
"3936f89d-7d96-43b5-adaf-f690b9de1298"
id
"_eb-arGgIuaaotQP4b7_6Ac"
is_byok
false
latency
1715
model_permaslug
"google/gemini-4-hydrogen-20261112"
provider_name
"Google"
status
200
total_cost
0.0129105
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
99.98%
Matches word count
n/a
neededClean
false
words
198
65.86%
Dialogue to Total Word Ratio
Ratio: 98.04%, Deviation: 8.04%
neededClean
false
wordsTotal
204
wordsDialogue
200
82.9203%