NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ94P15EJH0CXQ2YQVBD23N0
Run Details
Model:
Gemini 2.5 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
29.3s
Cost:
$0.016088
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.90%
Dialogue to Total Word Ratio
(details)
49.9515%
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
The air in Bill’s cramped garage, his self-proclaimed command center, reeked of stale coffee and his particular brand of over-earnest cologne. Bill himself hunched seriously over a glitter-covered birthday invitation, tracing a crayon-drawn dog with a jeweler’s loupe. His forehead was slick with concentration as he adjusted his ill-fitting, crumpled trench coat. Molly, meanwhile, leaned against a stack of deflated pool toys, idly sharpening a butter knife to an alarming point, humming tunelessly. Her tiny balaclava, a repurposed sleep mask, sat slightly askew. "Kids' party, Bill." He jabbed a finger at a crudely drawn gift table. "Strategic targets; high-value goods." His gaze darted to imaginary pressure plates. "Actual threats?" Molly prompted, testing the knife's edge. Bill peered at a hand-drawn security flowchart. "Juicebox traps. Anti-bouncy castle perimeter." He straightened, adjusting imaginary cufflinks. "Go time?" "Cake cutting." Bill's eyes gleamed with mercenary zeal, already sketching escape routes on the back of a grocery list. This precise infiltration, Operation Sugar Rush, would be flawless.
created_at
"2026-02-25T00:55:15.89Z"
2/25/2026, 12:55:15 AM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1440
moderation_latency
(null)
generation_time
29269
tokens_prompt
77
tokens_completion
3648
native_tokens_prompt
67
native_tokens_completion
6427
native_tokens_completion_images
0
native_tokens_reasoning
6196
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
usage
0.0160876
router
(null)
provider_responses
0
endpoint_id
"16c01e26-9b91-4d22-b487-ed35634b017d"
is_byok
false
latency
1440
model_permaslug
"google/gemini-2.5-flash"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771980915-hmdwroJEzvh4AWIkfUyu"
upstream_id
(null)
total_cost
0.0160876
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
162
99.90%
Dialogue to Total Word Ratio
Ratio: 11.76%, Deviation: 1.76%
neededClean
false
wordsTotal
170
wordsDialogue
20
49.9515%