NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCTMSXQG6TXTHJDDDB7N1B7
Run Details
Model:
Gemini 3.5 Flash Lite (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1.7s
Cost:
$0.000700
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
21.6892%
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
The blueprints for Bounce-A-Lot Castle fluttered in the damp alleyway between two industrial dumpsters. Molly adjusted her night-vision goggles, which were currently stuck on a setting that projected glowing pink unicorns across Bill’s terrified face. Bill wiped a stray speck of glitter from his trench coat and shivered. "Are you sure about this, Molly? The security is going to be ruthless." "Relax, Bill. It is just a room full of six-year-olds hopped up on juice boxes and unregulated sugar." "That is what makes it terrifying. Have you ever been drop-kicked by a toddler in a Batman costume?" "Once, but I was wearing inferior kneepads." "They have a piñata, Molly. It is essentially a papier-mâché claymore swinging from the rafters." "We stick to the plan. You disable the laser tripwires while I bypass the master-lock on the gift pile." "And if the clown wakes up?" "Feed him a balloon animal and run." "Right. For the record, if I am taken down by a rogue juice box, I am haunting your apartment forever." "Noted. Now sync your walkie-talkie and try not to sneeze this time."
created_at
"2026-07-25T14:25:09.567Z"
7/25/2026, 2:25:09 PM
model
"google/gemini-3.5-flash-lite-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
280
moderation_latency
(null)
generation_time
1597
tokens_prompt
75
tokens_completion
284
native_tokens_prompt
67
native_tokens_completion
272
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
0.0007001
router
(null)
provider_responses
0
endpoint_id
"6bd8f433-79e1-416c-b407-1772eb796c9a"
id
"RcdkasTGJ4LbjMcP8dCe-As"
is_byok
false
latency
280
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-1784989509-5AAdvqEYS3Ng6Kaw4sJK"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784989509-Kilzopr3XYWpQISnzWze"
upstream_id
"RcdkasTGJ4LbjMcP8dCe-As"
total_cost
0.0007001
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
43.38%
Matches word count
n/a
neededClean
false
words
183
0.00%
Dialogue to Total Word Ratio
Ratio: 73.44%, Deviation: 23.44%
neededClean
false
wordsTotal
192
wordsDialogue
141
21.6892%