NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8ZEE0WBEXY1A7G0XKMQGHV
Run Details
Model:
Gemini 3.1 Flash Lite
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.1s
Cost:
$0.000381
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3535%
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, the neon glow illuminating the frantic determination in her eyes as they crouched behind the bouncy castle. Damp grass soaked through Bill’s velvet tuxedo, but he remained focused on the target: a mountain of glitter-wrapped loot resting unguarded on a folding table near the lemonade fountain. The birthday clown, a man whose permanent greasepaint grin currently looked suspiciously sinister in the moonlight, juggled beanbags just ten yards away. Bill adjusted his tactical utility belt and shifted his weight. He could already taste the stolen loot, a mountain of plastic action figures and overpriced board games. Molly nudged his ribs with a sharp elbow, pointing toward the heavy-duty shed where the catering staff hid their keys. They had meticulously calculated the wind speed, the distraction interval of the sugar-crazed toddlers, and the exact rotation of the suburban security patrol. It was a flawless plan, provided nobody tripped over the inflatable dragon. Bill nudged her back, his expression grim. Are we actually doing this? Molly smirked, tightening her leather gloves until the knuckles turned white. We are absolutely stealing these presents. They lunged forward, melding perfectly into the chaotic shadows of the oversized party decorations.
created_at
"2026-05-10T12:57:54.98Z"
5/10/2026, 12:57:54 PM
model
"google/gemini-3.1-flash-lite-20260507"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
690
moderation_latency
(null)
generation_time
1956
tokens_prompt
77
tokens_completion
323
native_tokens_prompt
67
native_tokens_completion
243
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
0.00038125
router
(null)
provider_responses
0
endpoint_id
"237af107-d2e9-46c7-b146-c74d75980dee"
id
"04AAarGGDLuHz7IP5vL_wAg"
is_byok
false
latency
690
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-1778417874-yVCTVAB2BMIpauh6cy6S"
session_id
(null)
api_type
"completions"
id
"gen-1778417874-bAa1JSCLJplBAkObbKHD"
upstream_id
"04AAarGGDLuHz7IP5vL_wAg"
total_cost
0.00038125
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
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
200
wordsDialogue
0
68.3535%