NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-20-01KS25THP203ZX116PNGZDV710
Run Details
Model:
Gemini 3.5 Flash (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.5s
Cost:
$0.002540
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 checked her watch, her tactical visor reflecting the pastel chaos of the bouncy castle sixty yards away. Behind her, Bill was frantically trying to squeeze his six-foot-four frame into a neon-green dinosaur suit. The scent of spilled apple juice and desperation hung heavy in the warm afternoon air. "The security is tighter than we anticipated," Molly whispered, adjusting her binoculars to focus on a fierce-looking mother wielding a juice-box stapler. "My contact said the loot is hidden under the primary balloon arch." Bill struggled with his foam tail, knocking over a nearby recycling bin with a loud clatter. "My zipper is stuck on a sequin." Molly rolled her eyes and checked her map of the backyard. "Focus, Bill. We have a five-minute window when they sing the candle song. That’s our cue to sweep the gift table." "Is the getaway tricycle in position?" Bill muttered, his face grim behind the mesh mouth of the dinosaur. "It is," Molly replied, tapping her earpiece. "Just make sure you don't eat any cake this time." They crouched low in the azalea bushes, waiting for the high-pitched screams of sugar-fueled children to signal the start of their greatest, pettiest heist of the summer.
created_at
"2026-05-20T07:50:24.199Z"
5/20/2026, 7:50:24 AM
model
"google/gemini-3.5-flash-20260519"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
742
moderation_latency
(null)
generation_time
2401
tokens_prompt
77
tokens_completion
313
native_tokens_prompt
67
native_tokens_completion
271
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
0.0025395
router
(null)
provider_responses
0
endpoint_id
"bd50061c-e1d8-469e-96b1-d322e77378f8"
id
"wGcNapGhFZyG1MkPxf-7sQ0"
is_byok
false
latency
742
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-1779263424-Aw6oyILelXy01EbKuJNX"
session_id
(null)
api_type
"completions"
id
"gen-1779263424-hm5dXSuBu4duAbrcSEIQ"
upstream_id
"wGcNapGhFZyG1MkPxf-7sQ0"
total_cost
0.0025395
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
0.00%
Dialogue to Total Word Ratio
Ratio: 31.73%, Deviation: 21.73%
neededClean
false
wordsTotal
208
wordsDialogue
66
50.0000%