NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-20-01KS260660PNQR6AG6QTYZ08KF
Run Details
Model:
Gemini 3.5 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
4.7s
Cost:
$0.006112
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
3.62%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
1.8117%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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 adjusted the strap of her tactical diaper bag, her expression deadly serious as she stared at the blueprint spread across the hood of their hatchback. Bill was busy struggling to squeeze his six-foot-two frame into a remarkably tight, velvet Barney the Dinosaur suit. "We have precisely twelve minutes between the clown’s balloon animal segment and the serving of the ice cream cake," Molly said, tapping a red circle on the map. "That is our window." Bill gasped, tugging frantically at his purple neckline. "I can’t breathe, Molly. Is the tail supposed to wedge itself this far up my spine?" "Focus, Bill. This is the big leagues. We’re talking three pastel-wrapped Nintendo Switches, a vintage Lego castle, and at least forty envelope-based cash gifts from wealthy grandparents who forgot to buy actual toys." "But what about the target?" Bill asked, his voice muffled by the plush dinosaur head resting on his shoulder. "Seven-year-olds are vicious. Have you ever seen a child denied a juice box? They have the bite force of a pit bull." "That’s why you’re the distraction. You walk in, do some clumsy, oversized-lizard dancing, and dump a bucket of glitter on the patio. While they are blinded by the sparkle, I slip into the sunroom. I bag the loot, we meet at the getaway sedan, and we’re drinking margaritas by sunset." "And if the mother catches us?" Bill whispered, his eyes wide with genuine panic. "What if she demands to see my party-entertainer credentials?" "Tell her you’re a method actor," Molly snapped, sliding a pair of high-grip gardening gloves onto her hands. "Just don't make eye contact with the dad. He looks like a guy who takes his lawn care and his home security very seriously. Now, do you have the distraction material?" Bill reached into his purple pouch and pulled out a plastic tube. "I brought bubbles. High-velocity, tear-free bubbles." "Perfect. The slippery residue will create a natural barrier on the hardwood floor, slowing down any pursuing toddlers. What about the cake?" "What about it?" Bill asked. "Is it chocolate?" "Molly, we are international thieves, not monsters. We aren't stealing the cake." "I didn't say steal it, Bill. I said eat a slice while you’re in there. I'm starving." "I can't eat cake under fifty pounds of synthetic foam!" Bill cried, finally getting the dinosaur head over his face. His voice now sounded like it was coming from the bottom of a well. "How do I look?" Molly stared at the giant, slightly lopsided purple dinosaur standing in the alleyway. "You look like a nightmare that escaped from a public television studio. It’s perfect. Remember, no mercy. If a kid grabs your leg, you don’t kick, you just shake them off gently so we don’t get sued." "Got it," Bill’s muffled voice replied. "Gently shake the toddlers. Let's go get those presents."
created_at
"2026-05-20T07:53:29.03Z"
5/20/2026, 7:53:29 AM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
722
moderation_latency
(null)
generation_time
4631
tokens_prompt
77
tokens_completion
744
native_tokens_prompt
67
native_tokens_completion
668
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
0.0061125
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"eWgNap78CunTjMcPxOXhQA"
is_byok
false
latency
721
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-1779263609-DBxCNKkmE5Zj81cWQE5s"
session_id
(null)
api_type
"completions"
id
"gen-1779263609-rrjlx2lZyezlvmmdAf93"
upstream_id
"eWgNap78CunTjMcPxOXhQA"
total_cost
0.0061125
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
3.62%
Matches word count
n/a
neededClean
false
words
476
0.00%
Dialogue to Total Word Ratio
Ratio: 68.58%, Deviation: 38.58%
neededClean
false
wordsTotal
487
wordsDialogue
334
1.8117%