NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-19-01M7SVN4NTCESDXPTV7SSZK8BZ
Run Details
Model:
Gemini 4 Hydrogen (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
17.2s
Cost:
$0.016308
Provider:
Google
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9917%
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 blueprints across the stained kitchen table, weighting the corners with half-eaten donuts. The target was a suburban backyard, fortified by a bouncy castle and a perimeter of distracted parents. Bill squinted at the hand-drawn map, his brow furrowed in deep tactical concentration. They had spent three weeks casing the neighborhood, memorizing the exact arrival time of the balloon animal guy and the blind spots of the backyard patio. "Are you sure about the crazy clown?" Bill asked, tapping a grease-stained finger on the paper. "He's a total professional, Bill," Molly replied, adjusting her reading glasses. "He won't talk, and he's our best distraction." She traced their entry route through the overgrown hydrangeas, bypassing the treacherous slip-and-slide zone entirely. The haul was legendary: at least forty brightly wrapped boxes, likely containing top-tier plastic electronics and maybe even some cold, hard birthday cash from generous grandparents. Bill nodded slowly, admiring the sheer audacity of the operation. Once inside, they would have a four-minute window while the targets were distracted by a sugar-fueled piƱata frenzy. Molly rolled up the plans, a triumphant smirk playing on her lips. Tonight, they were taking candy from a baby, and nobody was going to stop them.
created_at
"2026-11-19T12:14:13.186Z"
11/19/2026, 12:14:13 PM
model
"google/gemini-4-hydrogen-20261112"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4426
moderation_latency
(null)
generation_time
17132
tokens_prompt
75
tokens_completion
767
native_tokens_prompt
97
native_tokens_completion
2155
native_tokens_completion_images
0
native_tokens_reasoning
1885
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
0.016308
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1795090453-Om3JSe3e4ZRKCdH8xrtB"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1795090453-x9gOdoMNS56p6VX4fY8C"
upstream_id
"Fej-aubtDq_tlOoP9qqq6Ak"
provider_responses
0
endpoint_id
"3936f89d-7d96-43b5-adaf-f690b9de1298"
id
"Fej-aubtDq_tlOoP9qqq6Ak"
is_byok
false
latency
4426
model_permaslug
"google/gemini-4-hydrogen-20261112"
provider_name
"Google"
status
200
total_cost
0.016308
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
202
100.00%
Dialogue to Total Word Ratio
Ratio: 9.52%, Deviation: 0.48%
neededClean
false
wordsTotal
210
wordsDialogue
20
99.9917%