NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR90ESTFFX423G34ADWZFTYV
Run Details
Model:
Gemini 3.1 Flash Lite
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.3s
Cost:
$0.000393
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.2661%
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 adjusted her neon bowtie, the cheap polyester scratching against her skin like a swarm of angry wasps. She stood behind a giant plastic sunflower, peering through the overgrown hedge at the backyard battlefield. Dozens of toddlers screeched in a frantic, sugar-fueled frenzy, their sticky fingers clutching balloons while a clown performed a lackluster routine with a deflated poodle. Beside her, Bill wrestled with a gargantuan sack shaped like a birthday cupcake. He was sweating profusely, his face turning a shade of purple that matched the streamers drooping from the patio roof. They were professionals, supposed legends of the criminal underworld, yet here they were, prepared to raid a suburban lawn for branded plastic toys and gift cards. The air hung heavy with the cloying, nauseating scent of strawberry frosting and impending chaos. Molly checked the stopwatch taped to her wrist, her emerald eyes darting toward the gift mountain resting unguarded near the inflatable castle. The perimeter was soft, the security guard currently being pelted with chocolate-covered marshmallows. It was perfect. She turned to her partner, nudging his ribs with a sharp elbow. Ready? Bill gripped the sack tight. Let us plunder. They lunged forward, blending into the shrieking madness of the bouncy house.
created_at
"2026-05-10T13:15:35.638Z"
5/10/2026, 1:15:35 PM
model
"google/gemini-3.1-flash-lite-20260507"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
661
moderation_latency
(null)
generation_time
2227
tokens_prompt
77
tokens_completion
328
native_tokens_prompt
67
native_tokens_completion
251
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
0.00039325
router
(null)
provider_responses
0
endpoint_id
"237af107-d2e9-46c7-b146-c74d75980dee"
id
"94QAasLbMoCsqtsP76-jEQ"
is_byok
false
latency
661
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-1778418935-4lGi51zdFv8sexBKrMAN"
session_id
(null)
api_type
"completions"
id
"gen-1778418935-eUyclOiKKmnjLs7vSSKi"
upstream_id
"94QAasLbMoCsqtsP76-jEQ"
total_cost
0.00039325
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
206
wordsDialogue
0
68.2661%