NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-19-01KS0TRHNCMY67V1Q215DEVTQ9
Run Details
Model:
Gemini 3.5 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
19.6s
Cost:
$0.044498
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
95.98%
Dialogue to Total Word Ratio
(details)
97.9912%
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
"We need to blend in, Bill," Molly whispered. "I bought a giant clown suit," Bill said proudly. "And squeaky shoes." "Squeaky shoes? For a stealth heist?" Molly groaned. "Are you insane?" "They distract the guards, Molly. The toddlers. They absolutely love squeaks." "Our targets are the presents in the bounce house archive. Not the toddlers." "I also packed apple juice boxes. For high stakes leverage." "Leverage? They are six, Bill. You do not negotiate with juice, you just swipe the Legos." "But what if there is a rival clown? A professional? He will see right through this makeup." "There is no rival clown. The party budget went to the pony. Which is your responsibility to distract." "Distract it with what?" "Carrots, Bill. I stuffed them in your tactical fanny pack." "This is a highly dangerous operation. What if the sugar rush hits early?" "Then we grab the Nintendo Switch boxes and run like hell. Do you have the decoy wrapped?" "Yes, a giant box of organic broccoli. Wrapped in unicorn paper. They will never open it." "Wait, is my face paint symmetrical?" Bill asked. "You look like a nightmare," Molly sighed. "Now, put the red nose on and let's move."
created_at
"2026-05-19T19:17:49.873Z"
5/19/2026, 7:17:49 PM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1420
moderation_latency
(null)
generation_time
19448
tokens_prompt
77
tokens_completion
1618
native_tokens_prompt
67
native_tokens_completion
4933
native_tokens_completion_images
0
native_tokens_reasoning
4640
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
0.0444975
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"XrcMauWoAtS__uMPhN2oyQI"
is_byok
false
latency
1420
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-1779218269-ji7Zx6aMIumpstrUyiG1"
session_id
(null)
api_type
"completions"
id
"gen-1779218269-mmXJnSU84fCk6IVNiwqe"
upstream_id
"XrcMauWoAtS__uMPhN2oyQI"
total_cost
0.0444975
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
95.98%
Dialogue to Total Word Ratio
Ratio: 94.50%, Deviation: 4.50%
neededClean
false
wordsTotal
200
wordsDialogue
189
97.9912%