Model

Llama 3.2 90B (Vision)

Test

Data extraction

Scenario

Who's the tallest?

Run ID

2024-09-26-01J8Q0PMQR8248ZBT58B9MMPH9

Model input

User/Human
Who is the tallest person based on the following text? Only return the name, nothing else. Jack is shorter than Jill. Jill is taller than Tom but shorter than Sarah. Mike is the same height as Jack.

Model response

AI
Sarah
id"gen-XqWyND0U9qHCN5jFMEjB7JGaA8Hw" 
total_cost0.0000324
upstream_id"chat-24dd0a03f6544fe4866531d8c3dd253e" 
created_at"2024-09-26T11:15:47.516154+00:00" Thursday, September 26th, 2024 at 11:15:47 AM GMT+00:00
model"meta-llama/llama-3.2-90b-vision-instruct" 
app_id182717
streamedtrue
cancelledfalse
provider_name"Hyperbolic" 
latency45
moderation_latency(null)
generation_time199
finish_reason"stop" 
tokens_prompt50
tokens_completion1
native_tokens_prompt78
native_tokens_completion3
native_tokens_reasoning(null)
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.0000324

Evaluation details

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