NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCWXDB0A1CTV1B1B4WZH6DP
Run Details
Model:
Gemini 3.6 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
5.7s
Cost:
$0.004338
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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
The balloons are my biggest concern, Molly whispered, pressing her face against the greasy diner window. Bill snorted into his lukewarm coffee. Balloons? We are robbing a seven-year-old, Molly. The only tactical threat is a hyperactive child with a sugar rush. You underestimate the noise footprint of a popped latex sphere, Bill. One wrong step and pop, the entire bouncy castle comes down on us. Fine, no balloons. What is the entry point? The doggy door in the kitchen. I am a grown man. I am not squeezing through a flap meant for a golden retriever. Then you can be the distraction. What kind of distraction? Put on the clown suit. Absolutely not. I have dignity. You are planning to steal Lego sets from a second grader, Bill. Your dignity left the building thirty minutes ago. I am a master thief, not Bozo. I wear black turtlenecks. Turtlenecks do not scream legitimate children's entertainment. The clown suit is in the trunk. It has a glitter nose. Does the nose squeak? Only when you press it hard. I hate you so much. What is the loot payload looking like? High value. Target acquired three major Star Wars sets, a drone, and a motorized ride-on mini Jeep. Can we drive the Jeep out? It has a top speed of four miles per hour. It is better than carrying forty pounds of plastic while wearing oversized red shoes. Fair point. But you are driving. I will be securing the juice boxes. Juice boxes? We are here for the toys, Molly! I need hydration, Bill. Pulling off the heist of the century in a suburban backyard takes stamina. It is Timmy’s birthday, not the Louvre. To Timmy, those presents are the Louvre. Which makes us top-tier international criminals. Or pathetic. Tomato, potato. Now, do you have the smoke bombs? I have the bath bombs. The store was out of tactical smoke. Bath bombs? If we drop them in the punch bowl, it creates a very alarming lavender-scented fizzing action. It will cause mass hysteria among the parents. That is actually evil. I love it. What about the cake? What about it? Are we taking it? It is ice cream cake. We are not stealing a child's cake, Molly. We have standards. It is mint chocolate chip, Bill. Load the cake into the Jeep. I knew you had a soul. Just give me the glitter nose. Let us go ruin a birthday.
created_at
"2026-07-25T15:04:48.746Z"
7/25/2026, 3:04:48 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
461
moderation_latency
(null)
generation_time
4891
tokens_prompt
75
tokens_completion
595
native_tokens_prompt
67
native_tokens_completion
565
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
"default"
usage
0.004338
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"kdBkasexIrrwjMcPoaWdmAw"
is_byok
false
latency
461
model_permaslug
"google/gemini-3.6-flash-20260721"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784991889-GVeMTR8PKoS32m2vaXWN"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784991889-BNIokSx2pbBbg5DtLXZj"
upstream_id
"kdBkasexIrrwjMcPoaWdmAw"
total_cost
0.004338
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
407
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 70.00%
neededClean
false
wordsTotal
412
wordsDialogue
0
0.0000%