Model Comparator

Compare up to four models using the same criteria.

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

Differences only

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

Model Comparator
Metrics	DeepSeek R1 Distill Llama 70B DeepSeek	Qwen3 VL 30B A3B Instruct Alibaba
Intelligence	7.9	7.9
Math	53.7	Best: 72.3
Speed	—	24 t/s
TTFT	—	3.05 s
Input · $ / 1M tokens	$0.70×2 relative to the lowest price among the compared models	Best: $0.35
Output · $ / 1M tokens	$1.10×1.8 relative to the lowest price among the compared models	Best: $0.60
Context window	128K	Best: 256K
Reasoning	Yes	No
Open weights	Yes	Yes

Intelligence

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

Math

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

Speed

DeepSeek R1 Distill Llama 70B: —
Qwen3 VL 30B A3B Instruct: 24 t/s

TTFT

DeepSeek R1 Distill Llama 70B: —
Qwen3 VL 30B A3B Instruct: 3.05 s

Input · $ / 1M tokens

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

Output · $ / 1M tokens

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

Context window

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

Reasoning

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

Open weights

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

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