Model

Llama 3.2 90B (Vision)

Test

Data extraction

Scenario

What's the color of the car?

Run ID

2024-09-26-01J8Q0RCY6BW2KSPX5A0B1KDS2

Model input

User/Human
What color is Sarah's car based on the following text? Only return the color, nothing else. John owns a blue car. Sarah's car is the same color as the sky on a clear day. Peter's car is red. The sky is not green on a clear day.

Model response

AI
Blue
id"gen-VVvInA9cPj4A3Rg7ymq1SUMW16fP" 
total_cost0.00007452
upstream_id"chat-52f78d3607e648ac8f4776d2ab1befcf" 
created_at"2024-09-26T11:16:45.248589+00:00" Thursday, September 26th, 2024 at 11:16:45 AM GMT+00:00
model"meta-llama/llama-3.2-90b-vision-instruct" 
app_id182717
streamedtrue
cancelledfalse
provider_name"Together" 
latency391
moderation_latency(null)
generation_time16
finish_reason"stop" 
tokens_prompt64
tokens_completion1
native_tokens_prompt67
native_tokens_completion2
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 insensitive: blue
 n/a
Pass Matches Regex
/\bblue\b/i
 n/a
100.0000%