NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR93EMBH2HNAB0JB3WFYZJ2J
Run Details
Model:
Gemini 3.1 Flash Lite
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.0s
Cost:
$0.000398
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.6885%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 reflecting off her dark jumpsuit. Bill, are your greasepaint wings secured tight? They are itching like crazy, Molly. Did we really need the fairy costumes? It is a princess party, Bill. Nobody questions a fairy floating toward the gift pile. You have the velvet sack? Stashed under my tutu. Are you certain the target is just toys? The parents are wealthy donors. It is fine jewelry hidden in the fancy boxes, not just plastic dolls. Do you have the distraction gas? One puff of this aerosol and the toddlers will be napping for three hours. Are we ready to breach the fence? Wait for the clown to start the balloon animal segment. That is our opening. I feel ridiculous, Molly. This is low, even for us. Shut up, Tinkerbell. Grab the sack. Why am I always the one crawling through the vents? Because you are the smallest fairy, Bill. Now, move your wings. The cake is being cut. We need to be inside before they finish singing. Fine, but if I get glitter in my eye, I am taking an extra cut of the diamonds. Agreed. Let go.
created_at
"2026-05-10T14:07:55.77Z"
5/10/2026, 2:07:55 PM
model
"google/gemini-3.1-flash-lite-20260507"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
564
moderation_latency
(null)
generation_time
1899
tokens_prompt
77
tokens_completion
288
native_tokens_prompt
67
native_tokens_completion
254
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
0.00039775
router
(null)
provider_responses
0
endpoint_id
"237af107-d2e9-46c7-b146-c74d75980dee"
id
"O5EAarHnO5OIqtsPu8ipKA"
is_byok
false
latency
564
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-1778422075-Tv4rWl4tVkY80e1weSEj"
session_id
(null)
api_type
"completions"
id
"gen-1778422075-mpv6HFR95WEeZSlhZ1lo"
upstream_id
"O5EAarHnO5OIqtsPu8ipKA"
total_cost
0.00039775
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
195
wordsDialogue
0
49.6885%