NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCVP189WKK9X97VV6RGB8ND
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
13.9s
Cost:
$0.021573
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
90.30%
Dialogue to Total Word Ratio
(details)
94.8372%
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
"Did you pack the smoke bombs?" Molly whispered, adjusting her dark tactical goggles. "Smoke bombs? Molly, it’s a six-year-old’s birthday party at a Bounce Emporium, not the Louvre," Bill hissed. "I brought juice boxes and a glitter gun." "Tactical brilliance. What’s our insertion point?" "The back patio. Past the terrifying inflatable slide. We drop in at fourteen hundred hours, right when the clown distracts the mark with balloon animals." "And the primary target?" "The gift table. A mountain of unopened Lego sets, three Nerf blasters, and a heavily wrapped box that smells like pure sugar." "Exquisite. What about local security?" "Toddlers. High on cake, entirely unpredictable. If a swarm approaches, throw gummy worms to create a diversion and fall back." "Got it. What if the mom brigade spots us?" "Claim you're the face painter. I'll offer to fix the sticky juice dispenser. Works every time." "Wait, what if the bouncy castle collapses?" "Then we grab the giant teddy bear and scatter into the woods." "And our getaway vehicle?" "We hotwire the electric Barbie Jeep parked in the driveway, load the stash, and haul tail before the piñata gets smashed." "You're a mastermind, Bill." "I try. Put on your conical party hat now. It’s heist time."
created_at
"2026-07-25T14:43:18.418Z"
7/25/2026, 2:43:18 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1448
moderation_latency
(null)
generation_time
13803
tokens_prompt
75
tokens_completion
1097
native_tokens_prompt
67
native_tokens_completion
2863
native_tokens_completion_images
0
native_tokens_reasoning
2554
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
0.021573
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"hstkap-KIcjZjMcP077SwQg"
is_byok
false
latency
1448
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-1784990598-0Ix5aIcY3RDjG675PVWX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784990598-e4J8NcsvaJO2H2zJ3jkw"
upstream_id
"hstkap-KIcjZjMcP077SwQg"
total_cost
0.021573
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
99.38%
Matches word count
n/a
neededClean
false
words
205
90.30%
Dialogue to Total Word Ratio
Ratio: 95.65%, Deviation: 5.65%
neededClean
false
wordsTotal
207
wordsDialogue
198
94.8372%