NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-19-01M7SVH9GG4NKSWPP4DYKQYXJK
Run Details
Model:
Gemini 4 Hydrogen (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
27.0s
Cost:
$0.032935
Provider:
Google
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 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
"Let me get this straight," Molly whispered, squinting at the crayon map. "We are robbing a little kid?" "Timmy’s parents are loaded," Bill replied, adjusting his black ski mask. "The gift table alone holds four grand in Lego sets." "What about security?" "A magician named Sparkles and a golden retriever." "Sparkles could be an undercover cop." "He pulls quarters from ears, Molly. He’s not the FBI." "Fine. How do we get past the bouncy castle?" "We deflate it. Create a diversion. While the toddlers cry, we sweep the table." "That’s cold, Bill. Even for us." "You want the Millennium Falcon set or not?" "Obviously I want it. Do we have disguises?" "I rented a giant Pikachu costume. You’re going in as Elsa." "I am not singing." "You don’t have to sing, just wave and grab the Barbie Dreamhouse." "What if Timmy recognizes my tattoos?" "Wear gloves. And watch out for the juice boxes. One spill and our getaway van smells like apple forever." "Wait. Who’s driving the van?" "My little nephew." "He’s twelve!" "He’s great at Mario Kart. Trust me." "We’re definitely going to prison." "Relax," Bill grinned, zipping his duffel bag. "It’s literally like taking candy from a baby."
created_at
"2026-11-19T12:12:07.062Z"
11/19/2026, 12:12:07 PM
model
"google/gemini-4-hydrogen-20261112"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1310
moderation_latency
(null)
generation_time
26976
tokens_prompt
75
tokens_completion
1227
native_tokens_prompt
97
native_tokens_completion
4372
native_tokens_completion_images
0
native_tokens_reasoning
4049
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
0.0329355
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1795090327-A3CmnyM1xiTPA8xz3U99"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1795090327-B2WbDqH97P76KGkAMjEe"
upstream_id
"l-f-arawBujbsbwP0LXVwQQ"
provider_responses
0
endpoint_id
"3936f89d-7d96-43b5-adaf-f690b9de1298"
id
"l-f-arawBujbsbwP0LXVwQQ"
is_byok
false
latency
1309
model_permaslug
"google/gemini-4-hydrogen-20261112"
provider_name
"Google"
status
200
total_cost
0.0329355
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: 90.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
180
100.0000%