Model Comparator

Compare up to four models using the same criteria.

Llama 3.3 Instruct 70B
Meta
Qwen2.5 Instruct 72B
Alibaba

Differences only

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

Model Comparator
Metrics	Llama 3.3 Instruct 70B Meta	Qwen2.5 Instruct 72B Alibaba
Intelligence	7.7	7.7
Coding	11.9	—
Math	7.7	Best: 14
Speed	Best: 92.8 t/s	30.4 t/s
TTFT	Best: 1.71 s	3.9 s
Input · $ / 1M tokens	$0.71×1.5 relative to the lowest price among the compared models	Best: $0.475
Output · $ / 1M tokens	$0.72×1.5 relative to the lowest price among the compared models	Best: $0.495
Context window	128K	Best: 131K
Reasoning	No	No
Open weights	Yes	Yes

Intelligence

Llama 3.3 Instruct 70B: 7.7
Qwen2.5 Instruct 72B: 7.7

Coding

Llama 3.3 Instruct 70B: 11.9
Qwen2.5 Instruct 72B: —

Math

Llama 3.3 Instruct 70B: 7.7
Qwen2.5 Instruct 72B: Best: 14

Speed

Llama 3.3 Instruct 70B: Best: 92.8 t/s
Qwen2.5 Instruct 72B: 30.4 t/s

TTFT

Llama 3.3 Instruct 70B: Best: 1.71 s
Qwen2.5 Instruct 72B: 3.9 s

Input · $ / 1M tokens

Llama 3.3 Instruct 70B: $0.71×1.5 relative to the lowest price among the compared models
Qwen2.5 Instruct 72B: Best: $0.475

Output · $ / 1M tokens

Llama 3.3 Instruct 70B: $0.72×1.5 relative to the lowest price among the compared models
Qwen2.5 Instruct 72B: Best: $0.495

Context window

Llama 3.3 Instruct 70B: 128K
Qwen2.5 Instruct 72B: Best: 131K

Reasoning

Llama 3.3 Instruct 70B: No
Qwen2.5 Instruct 72B: No

Open weights

Llama 3.3 Instruct 70B: Yes
Qwen2.5 Instruct 72B: 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.

Llama 3.3 Instruct 70B7.7 · $0.712
Qwen2.5 Instruct 72B7.7 · $0.48