NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8ZAEZD5Z4TTQA791MZF97Z
Run Details
Model:
Gemini 3.1 Flash Lite (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.1s
Cost:
$0.000377
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 adjusted her neon tutu and checked the perimeter of the backyard. Bill crouched behind a plastic slide, sweating profusely in a giant plush frog suit. We are definitely going to prison for this, Bill hissed while adjusting his rubber thumb. Molly rolled her eyes and signaled toward the stack of colorful boxes. Prison is a strong word for petty theft at a unicorn-themed birthday party, she whispered back. Bill groaned as a group of toddlers shrieked in the distance. They have the eyes of predators, Molly, he countered while pointing at a kid holding a juice box. Stop being a coward and grab the glittery one, she ordered as she crouched lower. Is the loot even worth the psychological trauma of this mascot costume, Bill asked. It is worth five thousand dollars in vintage toys, Molly replied with a smirk. Bill sighed and waddled toward the pile, his webbed feet squeaking loudly against the synthetic grass. Stop squeaking, she hissed while grabbing a large box. I am trying, he growled as a balloon animal popped nearby. We leave in ten seconds, Molly commanded. Bill snatched a mountain of presents, their eyes meeting in silent, ridiculous desperation.
created_at
"2026-05-10T12:55:44.885Z"
5/10/2026, 12:55:44 PM
model
"google/gemini-3.1-flash-lite-20260507"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
567
moderation_latency
(null)
generation_time
2004
tokens_prompt
77
tokens_completion
293
native_tokens_prompt
67
native_tokens_completion
240
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
0.00037675
router
(null)
provider_responses
0
endpoint_id
"237af107-d2e9-46c7-b146-c74d75980dee"
id
"UYAAatbGBf2Hz7IP9eqa4Qc"
is_byok
false
latency
567
model_permaslug
"google/gemini-3.1-flash-lite-20260507"
provider_name
"Google AI Studio"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778417744-k9aPBMFwFwSt0xQo8Fdr"
session_id
(null)
api_type
"completions"
id
"gen-1778417744-BdAitfKQKcwP27VYgfIB"
upstream_id
"UYAAatbGBf2Hz7IP9eqa4Qc"
total_cost
0.00037675
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 50.00%
neededClean
false
wordsTotal
198
wordsDialogue
0
49.9595%