NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCSDRCCZ6GGKX8JZZTSFG09
Run Details
Model:
Gemini 3.6 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.2s
Cost:
$0.018393
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
95.31%
Dialogue to Total Word Ratio
(details)
65.1575%
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
"Alright Bill, the target is Timmy’s seventh birthday," Molly whispered, pointing at the blueprint. "Infiltration happens during the pinata assault." "Pinata? That's suicide, Molly! Those sugar-crazed six-year-olds go rabid when candy hits the grass!" Bill gasped. "What about the perimeter guard?" "It's a three-pound Pomeranian named Sprinkles. I've neutralized him with a slice of sharp cheddar." "Brilliant. Now, where is the main vault?" "The gift table in the sunroom. High-value loot: three Lego Death Stars, a Nintendo Switch, and a suspiciously heavy envelope from Grandma." "Sweet mother of plastic," Bill breathed. "What's our extraction route?" "Through the bouncy castle. We slide down the dragon tail, scale the wooden fence, and disappear into the alley before musical chairs begins." "Wait, what if the clown spots us?" "Barnaby? He’s in my pocket, Bill. I promised him twenty percent of the Roblox gift cards." "You're a cold monster, Molly." "I'm a professional. Strap on your juice-box holster. We breach at cake time." "If we pull this off, we’ll be swimming in Nerf darts!" "Focus! Remember, no child gets left un-robbed." "Copy that. For the Legos!"
created_at
"2026-07-25T14:03:50.039Z"
7/25/2026, 2:03:50 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1617
moderation_latency
(null)
generation_time
11149
tokens_prompt
75
tokens_completion
1034
native_tokens_prompt
67
native_tokens_completion
2439
native_tokens_completion_images
0
native_tokens_reasoning
2133
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
0.018393
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"RsJkaqblB5ut-8YP4ZGFiAU"
is_byok
false
latency
1617
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-1784988230-HosNE6sFrUAxHg3w6b5f"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784988230-I41Vq9Xu9isJb2a4zuh5"
upstream_id
"RsJkaqblB5ut-8YP4ZGFiAU"
total_cost
0.018393
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
35.00%
Matches word count
n/a
neededClean
false
words
182
95.31%
Dialogue to Total Word Ratio
Ratio: 94.68%, Deviation: 4.68%
neededClean
false
wordsTotal
188
wordsDialogue
178
65.1575%