NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCXRTTA1TQFJXAF53J0SPKA
Run Details
Model:
Gemini 3.6 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.4s
Cost:
$0.002223
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
25.9628%
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
Look at all those tiny, glittering boxes, Bill whispered, adjusting his binoculars. Those are for a seven-year-old, Molly snapped. And that seven-year-old is suddenly the wealthiest kid on the block, Bill countered. Have you seen the size of that red one? It’s practically screaming high-end Lego set. We are professional cat burglars, Molly said, pinching the bridge of her nose. We do not rob bounce houses. We rob opportunities, Molly. Opportunities wrapped in paw-patrol paper. Now, what’s the tactical entry point? The slide? Molly asked sarcastically. Brilliant, Bill said. I’ll distract the clown with a fake balloon animal crisis, you slip past the piñata, secure the loot bag, and meet me by the juice boxes. What about the hyperventilating swarm of children? Molly gestured wildly at the lawn. They’re like tiny, sugar-crazed attack dogs. I brought cake, Bill replied, pulling a frosted wedge from his jacket. Nobody suspects the guy distributing unauthorized baked goods. That’s biological warfare, Bill. It’s strategy, Molly. Now, pull your mask down. It’s a glittery unicorn mask, Molly groaned. It offers complete anonymity and festive integration, Bill insisted. Move out!
created_at
"2026-07-25T15:19:47.283Z"
7/25/2026, 3:19:47 PM
model
"google/gemini-3.6-flash-20260721"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
536
moderation_latency
(null)
generation_time
3340
tokens_prompt
75
tokens_completion
312
native_tokens_prompt
67
native_tokens_completion
283
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
0.002223
router
(null)
provider_responses
0
endpoint_id
"5d6d133d-a953-4781-a835-7ee76f4e1388"
id
"E9RkauGHGdaUjrEPkbefwAU"
is_byok
false
latency
536
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-1784992787-9CqzEaU0lZMOcEqNqcBG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784992787-XXz5LL9oNair6P8Q7Ybb"
upstream_id
"E9RkauGHGdaUjrEPkbefwAU"
total_cost
0.002223
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
51.93%
Matches word count
n/a
neededClean
false
words
184
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
191
wordsDialogue
0
25.9628%