Model Comparator

Compare up to four models using the same criteria.

Qwen3 VL 30B A3B Instruct
Alibaba
DeepSeek R1 Distill Llama 70B
DeepSeek

Differences only

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

Model Comparator
Metrics	Qwen3 VL 30B A3B Instruct Alibaba	DeepSeek R1 Distill Llama 70B DeepSeek
Intelligence	7.9	7.9
Math	Best: 72.3	53.7
Speed	23.8 t/s	—
TTFT	3.22 s	—
Input · $ / 1M tokens	Best: $0.35	$0.70×2 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.60	$1.10×1.8 relative to the lowest price among the compared models
Context window	Best: 256K	128K
Reasoning	No	Yes
Open weights	Yes	Yes

Intelligence

Qwen3 VL 30B A3B Instruct: 7.9
DeepSeek R1 Distill Llama 70B: 7.9

Math

Qwen3 VL 30B A3B Instruct: Best: 72.3
DeepSeek R1 Distill Llama 70B: 53.7

Speed

Qwen3 VL 30B A3B Instruct: 23.8 t/s
DeepSeek R1 Distill Llama 70B: —

TTFT

Qwen3 VL 30B A3B Instruct: 3.22 s
DeepSeek R1 Distill Llama 70B: —

Input · $ / 1M tokens

Qwen3 VL 30B A3B Instruct: Best: $0.35
DeepSeek R1 Distill Llama 70B: $0.70×2 relative to the lowest price among the compared models

Output · $ / 1M tokens

Qwen3 VL 30B A3B Instruct: Best: $0.60
DeepSeek R1 Distill Llama 70B: $1.10×1.8 relative to the lowest price among the compared models

Context window

Qwen3 VL 30B A3B Instruct: Best: 256K
DeepSeek R1 Distill Llama 70B: 128K

Reasoning

Qwen3 VL 30B A3B Instruct: No
DeepSeek R1 Distill Llama 70B: Yes

Open weights

Qwen3 VL 30B A3B Instruct: Yes
DeepSeek R1 Distill Llama 70B: 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.

Qwen3 VL 30B A3B Instruct7.9 · $0.412
DeepSeek R1 Distill Llama 70B7.9 · $0.80