NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRS8Y4RB7NW1S74E21XWY4
Run Details
Model:
Gemini 3.7 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.5s
Cost:
$0.010967
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
72.42%
Dialogue to Total Word Ratio
(details)
86.1695%
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
Molly smoothed the crayon map. "The target is loaded with high-end Lego sets, Bill." "Heavy security?" "A clown named Bip-Bop. He is ruthless with balloon swords, but easily distracted by cheap juice boxes." "What about perimeter defense?" "A massive bouncy castle covers the east lawn. We will use it for tactical extraction." "Brilliant. And the loot?" "Piled high in the sunroom behind a fortress of streamers and three sugar-crazed toddlers." "Those ankle-biters are completely unpredictable, Molly. Do we have naptime coordinates?" "Two-fifteen sharp. Once the donkey pinata drops, utter chaos ensues. That is our five-minute window." "I will wear the mascot suit." "No, the giant badger outfit smells like old cabbage. Wear the magician disguise." "Fine, but you handle the getaway wagon." "The Radio Flyer is fully greased. We grab the drones, the video games, and every single wrapped box." "What if the birthday boy's mother spots us?" "Offer her a mimosa and run like hell." "What about glitter bombs in the gift bags?" "Glitter is forensic evidence, Bill. Avoid it at all costs." "Copy that. Cake, cash, and carnage." "Leave the cake. We are professionals." "Right. Strictly the toys." "Synchronize watches. Operation Juice Box is go."
created_at
"2026-09-03T13:54:25.356Z"
9/3/2026, 1:54:25 PM
model
"google/gemini-3.7-flash-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1280
moderation_latency
(null)
generation_time
8408
tokens_prompt
75
tokens_completion
1123
native_tokens_prompt
67
native_tokens_completion
2911
native_tokens_completion_images
0
native_tokens_reasoning
2596
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
0.0109665
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443665-u9dzq7QjxiL7qsd79u41"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443665-ehdRjdpO8o5WQXjDbK4Q"
upstream_id
"EXyZaqDpHfK8sOIP6ZTy0Qk"
provider_responses
0
endpoint_id
"dd072012-3274-417d-97e3-e290cba37e31"
id
"EXyZaqDpHfK8sOIP6ZTy0Qk"
is_byok
false
latency
1276
model_permaslug
"google/gemini-3.7-flash-20260813"
provider_name
"Google AI Studio"
status
200
total_cost
0.0109665
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
72.42%
Dialogue to Total Word Ratio
Ratio: 97.54%, Deviation: 7.54%
neededClean
false
wordsTotal
203
wordsDialogue
198
86.1695%