Model

Llama 3.2 90B (Vision)

Test

Data extraction

Scenario

Who's the sister?

Run ID

2024-09-26-01J8Q0QHX4866E140K701GC3EY

Model input

User/Human
Who is the sister of Sandie based on the following text? Only return the name, nothing else. Sandie has a doll named Lulu, she carries it around all day. She says she's her little sister, but her actual sister's name is Cassie.

Model response

AI
Cassie
id"gen-nEexKIjQT28ZbIn1512KupsG0cdQ" 
total_cost0.00007452
upstream_id"chat-0b7fa09131fa4e7788a170c9f6552c1e" 
created_at"2024-09-26T11:16:17.60106+00:00" Thursday, September 26th, 2024 at 11:16:17 AM GMT+00:00
model"meta-llama/llama-3.2-90b-vision-instruct" 
app_id182717
streamedtrue
cancelledfalse
provider_name"Together" 
latency396
moderation_latency(null)
generation_time62
finish_reason"stop" 
tokens_prompt62
tokens_completion3
native_tokens_prompt65
native_tokens_completion4
native_tokens_reasoning(null)
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.00007452

Evaluation details

Result Evaluator Details Meta Data
Pass Matches text
Case sensitive: Cassie
n/a
Pass Matches Regex
/\bCassie\b/
n/a
100.0000%