NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-20-01KS25RG731FF17WS5XKQXBFE2
Run Details
Model:
Gemini 3.5 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.4s
Cost:
$0.002495
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
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
Are you sure about the clown suits, Bill? Molly, it is the perfect camouflage. No one questions a clown. But I hate makeup, and these shoes are three sizes too big. How are we supposed to make a quick getaway if we are tripping over our own feet? We will not need to run. We just walk in, blend with the magicians, bag the loot, and walk out. And the target? Seven-year-old Toby's birthday bash. The gift table is near the bounce house. It is a goldmine of unopened consoles, drone toys, and cash-stuffed envelopes from grandparents. What about the parents? Distracted by cake and toddler chaos. I will initiate a balloon animal distraction. While they queue for balloon poodles, you bag the presents in this oversized sack. And if a child asks for a balloon? You twist it into a sword and tell them to go play. Are you seriously expecting me to rob a child while wearing squeaky shoes? Yes. Now put on your red nose, Molly. The bouncy castle is deflating, which means cake is served, and our window of opportunity is opening. This is a new low for us, Bill. A profitable low. Grab the sack.
created_at
"2026-05-20T07:49:17.16Z"
5/20/2026, 7:49:17 AM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
772
moderation_latency
(null)
generation_time
2342
tokens_prompt
77
tokens_completion
296
native_tokens_prompt
67
native_tokens_completion
266
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
"standard"
usage
0.0024945
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"fWcNarGhEuasjrEP3OehiAc"
is_byok
false
latency
772
model_permaslug
"google/gemini-3.5-flash-20260519"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer
(null)
request_id
"req-1779263357-rQAxHZKwaHTOMMx2HQQ1"
session_id
(null)
api_type
"completions"
id
"gen-1779263357-KlKyRROEfszMMStnypct"
upstream_id
"fWcNarGhEuasjrEP3OehiAc"
total_cost
0.0024945
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
203
wordsDialogue
0
50.0000%