Model Comparator

Compare up to four models using the same criteria.

Reka Flash (Sep '24)
Reka AI
Llama 3.2 Instruct 90B (Vision)
Meta

Differences only

✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.

Model Comparator
Metrics	Reka Flash (Sep '24) Reka AI	Llama 3.2 Instruct 90B (Vision) Meta
Intelligence	6.4	6.4
Input · $ / 1M tokens	$0.20	—
Output · $ / 1M tokens	$0.80	—
Context window	128K	128K
Reasoning	No	No
Open weights	No	Yes

Intelligence

Reka Flash (Sep '24): 6.4
Llama 3.2 Instruct 90B (Vision): 6.4

Input · $ / 1M tokens

Reka Flash (Sep '24): $0.20
Llama 3.2 Instruct 90B (Vision): —

Output · $ / 1M tokens

Reka Flash (Sep '24): $0.80
Llama 3.2 Instruct 90B (Vision): —

Context window

Reka Flash (Sep '24): 128K
Llama 3.2 Instruct 90B (Vision): 128K

Reasoning

Reka Flash (Sep '24): No
Llama 3.2 Instruct 90B (Vision): No

Open weights

Reka Flash (Sep '24): No
Llama 3.2 Instruct 90B (Vision): Yes

Each reasoning level remains a separate configuration.

Score and cost

Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.

Reka Flash (Sep '24)6.4 · $0.35

Not plotted for lack of data on these axes: Llama 3.2 Instruct 90B (Vision).