Model Comparator

Compare up to four models using the same criteria.

Llama 3.2 Instruct 90B (Vision)
Meta
Qwen2.5 Turbo
Alibaba

Differences only

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

Model Comparator
Metrics	Llama 3.2 Instruct 90B (Vision) Meta	Qwen2.5 Turbo Alibaba
Intelligence	6.4	6.4
Speed	—	85.2 t/s
TTFT	—	2.15 s
Input · $ / 1M tokens	—	$0.050
Output · $ / 1M tokens	—	$0.20
Context window	128K	Best: 1M
Reasoning	No	No
Open weights	Yes	No

Intelligence

Llama 3.2 Instruct 90B (Vision): 6.4
Qwen2.5 Turbo: 6.4

Speed

Llama 3.2 Instruct 90B (Vision): —
Qwen2.5 Turbo: 85.2 t/s

TTFT

Llama 3.2 Instruct 90B (Vision): —
Qwen2.5 Turbo: 2.15 s

Input · $ / 1M tokens

Llama 3.2 Instruct 90B (Vision): —
Qwen2.5 Turbo: $0.050

Output · $ / 1M tokens

Llama 3.2 Instruct 90B (Vision): —
Qwen2.5 Turbo: $0.20

Context window

Llama 3.2 Instruct 90B (Vision): 128K
Qwen2.5 Turbo: Best: 1M

Reasoning

Llama 3.2 Instruct 90B (Vision): No
Qwen2.5 Turbo: No

Open weights

Llama 3.2 Instruct 90B (Vision): Yes
Qwen2.5 Turbo: No

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.

Qwen2.5 Turbo6.4 · $0.088

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