NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCWJGWE5EYF2CS14GPM3A61
Run Details
Model:
Gemini 3.5 Flash Lite (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1.6s
Cost:
$0.000610
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
40.6364%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 checked her watch while nervously adjusting the oversized clown nose that kept sliding down her sweaty upper lip. Bill was currently struggling to zip himself into a hideous foam-rubber unicorn costume that smelled strongly of mothballs and stale popcorn. The stakes were undeniably high because today they were targeting the ultimate high-security vault of chaotic evil known as little Timmy’s seventh birthday party. Are you sure the distraction protocol is fully loaded and ready to deploy? Bill asked, his muffled voice echoing comically from deep inside the horned horse head. I tested the catapult myself, Molly whispered sharply, tapping a bulging burlap sack against her striped knee socks. Those toddlers will be completely incapacitated by an unprecedented avalanche of hyper-concentrated glitter and unauthorized juice boxes. Just make sure you grab the jumbo-sized remote-controlled helicopter before some drooling menace licks the landing gear, Bill grumbled, waddling awkwardly toward the bouncy castle perimeter. Focus, partner, Molly hissed, pulling down her rainbow wig with criminal determination. We do this for the loot, the glory, and absolutely nothing to do with the fact that neither of us ever got a pony.
created_at
"2026-07-25T14:58:51.925Z"
7/25/2026, 2:58:51 PM
model
"google/gemini-3.5-flash-lite-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
278
moderation_latency
(null)
generation_time
1578
tokens_prompt
75
tokens_completion
314
native_tokens_prompt
67
native_tokens_completion
236
native_tokens_completion_images
0
native_tokens_reasoning
0
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
0.0006101
router
(null)
provider_responses
0
endpoint_id
"6bd8f433-79e1-416c-b407-1772eb796c9a"
id
"K89kaqHVO-yW-8YP_ai40Qg"
is_byok
false
latency
278
model_permaslug
"google/gemini-3.5-flash-lite-20260721"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784991531-pUnA7gYMLi2i890G9fYr"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784991531-4Ga3bbs6NTL0HL4kMs0S"
upstream_id
"K89kaqHVO-yW-8YP_ai40Qg"
total_cost
0.0006101
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
188
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 50.00%
neededClean
false
wordsTotal
193
wordsDialogue
0
40.6364%