NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HHYWTQTP15N4GAF3ANWY68
Run Details
Model:
Gemini 3.8 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
16.0s
Cost:
$0.022130
Provider:
Google AI Studio
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
Molly peered through the hedges and tapped the diagram. "Put on the snout, Bill. Zero hour approaches." "Do I have to be Peppa Pig? The rubber snout chafes my nose, Molly." "Professionals endure chafing. Look: bounce house on the perimeter, juice station dead ahead, and the mother lode, the gift table, beside the patio doors." Bill adjusted his foam ears and groaned nervously. "What about the hostiles?" "Ten toddlers, hopped up on blue raspberry frosting. Highly volatile, zero discipline. If they swarm, deploy the decoy." "The smoke grenade?" "The animal crackers, idiot! Then we bag the loot. Little Timmy’s getting a drone, Bill. A high-spec quadcopter with night vision. It belongs in a pawn shop, not his sticky, ungrateful hands." "What if the clown intervenes? He looks shifty." "Binky? He makes thirty bucks an hour. He won't risk his neck for a plastic kitchen playset. Now, is your sack ready?" "Sack ready, snout secured, pockets stuffed with fruit snacks." "Remember our code: ruthless, silent, undetectable." "Wait, is that double-fudge chocolate cake?" She glared hard. "Eyes on the prize, you fool! We take the Lego Millennium Falcon first, then the video games, then the bicycle. Move in three, two, one, crawl!"
created_at
"2026-09-02T17:16:40.702Z"
9/2/2026, 5:16:40 PM
model
"google/gemini-3.8-flash-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1242
moderation_latency
(null)
generation_time
15874
tokens_prompt
75
tokens_completion
1939
native_tokens_prompt
67
native_tokens_completion
5888
native_tokens_completion_images
0
native_tokens_reasoning
5580
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
0.02213025
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788369400-3wwHH4aP3PwawAJifQfI"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788369400-rLzhadfHHU9EuQokN6su"
upstream_id
"-FmYatm9MOLh_uMP277QoQE"
provider_responses
0
endpoint_id
"d376f781-516d-42f9-936d-46f19abca6cc"
id
"-FmYatm9MOLh_uMP277QoQE"
is_byok
false
latency
1242
model_permaslug
"google/gemini-3.8-flash-20260902"
provider_name
"Google AI Studio"
status
200
total_cost
0.02213025
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
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: 90.10%, Deviation: 0.10%
neededClean
false
wordsTotal
202
wordsDialogue
182
100.0000%