Model

Llama 3.2 90B (Vision)

Test

Data extraction

Scenario

Guess the pet

Run ID

2024-09-26-01J8Q0QPCTCQ71K02ADNZ3P7GS

Model input

User/Human
What pet does Emma own based on the following text? Only return the pet type, nothing else. John has a dog. Sarah owns a cat. Emma's pet purrs and has whiskers. Peter has a hamster.

Model response

AI
Cat.
id"gen-qij3h9fLdXOCSQQVe5WIn2nyK8xo" 
total_cost0.00006372
upstream_id"chat-ae0d1b3213a045fdbf479529436f1a3a" 
created_at"2024-09-26T11:16:22.337393+00:00" Thursday, September 26th, 2024 at 11:16:22 AM GMT+00:00
model"meta-llama/llama-3.2-90b-vision-instruct" 
app_id182717
streamedtrue
cancelledfalse
provider_name"Together" 
latency502
moderation_latency(null)
generation_time37
finish_reason"stop" 
tokens_prompt53
tokens_completion2
native_tokens_prompt56
native_tokens_completion3
native_tokens_reasoning(null)
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.00006372

Evaluation details

Result Evaluator Details Meta Data
Fail Matches text
Case insensitive: cat
 n/a
Pass Matches Regex
/\bcat\b/i
 n/a
50.0000%