NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-20-01KS25W8XX4VDK5QHHWV5Y5N4B
Run Details
Model:
Gemini 3.5 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.3s
Cost:
$0.002207
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
10.0948%
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
Now or never, Bill. Put on the nose. I am not wearing the giant foam nose, Molly. It insults my dignity as a master thief. Your dignity won’t bypass the biometric security of a bouncy castle, but this clown suit will. Did you pack the distraction? Yes, thirty helium balloons and a canister of defense-grade itching powder. But how do we locate the vault? It is a pile of brightly wrapped boxes next to the juice-box station. Focus, Bill. Once the cake is served, the guards are completely incapacitated by sugar crashes. That is our window. And the target? The birthday boy? Seven years old. Ruthless. He has a trained golden retriever and a water balloon slingshot. If he spots us, we are compromised. Do you have the decoy? I brought a generic action figure and a card with ten dollars in it. He won’t know the difference until we are halfway to the getaway tricycle. Excellent. Hand me the face paint. We are going to rob these toddlers blind. For greasepaint and glory, Molly. Let us secure the loot.
created_at
"2026-05-20T07:51:20.77Z"
5/20/2026, 7:51:20 AM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
735
moderation_latency
(null)
generation_time
2186
tokens_prompt
77
tokens_completion
269
native_tokens_prompt
67
native_tokens_completion
234
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
0.0022065
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"-GcNaun5N8-x1MkP2KzB4Qk"
is_byok
false
latency
735
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-1779263480-kVpLVNmcSnFO541OVdbI"
session_id
(null)
api_type
"completions"
id
"gen-1779263480-RbvhUO7XLlYi5lZwxMEP"
upstream_id
"-GcNaun5N8-x1MkP2KzB4Qk"
total_cost
0.0022065
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
182
wordsDialogue
0
10.0948%