NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRJDNYF0BXPGGC1F7PZ1QP
Run Details
Model:
Gemini 3.7 Flash (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.6s
Cost:
$0.008072
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
65.99%
Dialogue to Total Word Ratio
(details)
82.9863%
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 seriously wearing the giant inflatable dinosaur costume?" Molly asked. "It provides maximum stealth and undeniable cuteness," Bill replied. "Children inherently trust apex predators." "We are robbing a seven-year-old’s backyard birthday party, Bill, not infiltrating a high-security vault." "Timmy’s parents are hedge fund billionaires, Molly. The gift pile contains rare consoles, titanium scooters, and possibly bearer bonds hidden in teddy bears." "Can you even sprint in that thing without toppling over?" "I have practiced. What is your entry strategy?" "I bribed the balloon artist. The moment the magic show starts, I will deploy the decoy pinata." "Is it filled with angry hornets?" "No, glitter and gluten-free broccoli puffs. It will trigger absolute pandemonium among the helicopter parents." "Sheer tactical genius. When do we secure the payload?" "Precisely at three-fifteen during musical chairs. When the music cuts, the kids freeze in terror. That gives us forty seconds." "And the extraction route?" "The inflatable bouncy castle has an emergency flap. We slide out, vault the garden fence, and toss the bags into the getaway minivan." "What about the clown guarding the juice boxes?" "Avoid eye contact. He looks like he has served federal time." "Understood. Commencing operation birthday bash."
created_at
"2026-09-03T13:50:40.836Z"
9/3/2026, 1:50:40 PM
model
"google/gemini-3.7-flash-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1419
moderation_latency
(null)
generation_time
6531
tokens_prompt
75
tokens_completion
913
native_tokens_prompt
67
native_tokens_completion
2139
native_tokens_completion_images
0
native_tokens_reasoning
1843
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
0.0080715
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443440-wMREvRIPw0BoLkKcp6MM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443440-EWdiJanbZborgijPGSag"
upstream_id
"MHuZap3eOqPQjMcPutmU6AY"
provider_responses
0
endpoint_id
"dd072012-3274-417d-97e3-e290cba37e31"
id
"MHuZap3eOqPQjMcPutmU6AY"
is_byok
false
latency
1418
model_permaslug
"google/gemini-3.7-flash-20260813"
provider_name
"Google AI Studio"
status
200
total_cost
0.0080715
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
99.98%
Matches word count
n/a
neededClean
false
words
198
65.99%
Dialogue to Total Word Ratio
Ratio: 98.03%, Deviation: 8.03%
neededClean
false
wordsTotal
203
wordsDialogue
199
82.9863%