Model Comparator

Compare up to four models using the same criteria.

DeepSeek V3.1 (Reasoning)
DeepSeek
Qwen3 VL 235B A22B (Reasoning)
Alibaba

Differences only

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

Model Comparator
Metrics	DeepSeek V3.1 (Reasoning) DeepSeek	Qwen3 VL 235B A22B (Reasoning) Alibaba
Intelligence	Best: 13.5	13.4
Math	Best: 89.7	88.3
Speed	Best: 119 t/s	57.1 t/s
TTFT	3.45 s	Best: 2.73 s
Input · $ / 1M tokens	$0.58×1.4 relative to the lowest price among the compared models	Best: $0.40
Output · $ / 1M tokens	Best: $1.68	$4×2.4 relative to the lowest price among the compared models
Context window	128K	Best: 262K
Reasoning	Yes	Yes
Open weights	Yes	Yes

Intelligence

DeepSeek V3.1 (Reasoning): Best: 13.5
Qwen3 VL 235B A22B (Reasoning): 13.4

Math

DeepSeek V3.1 (Reasoning): Best: 89.7
Qwen3 VL 235B A22B (Reasoning): 88.3

Speed

DeepSeek V3.1 (Reasoning): Best: 119 t/s
Qwen3 VL 235B A22B (Reasoning): 57.1 t/s

TTFT

DeepSeek V3.1 (Reasoning): 3.45 s
Qwen3 VL 235B A22B (Reasoning): Best: 2.73 s

Input · $ / 1M tokens

DeepSeek V3.1 (Reasoning): $0.58×1.4 relative to the lowest price among the compared models
Qwen3 VL 235B A22B (Reasoning): Best: $0.40

Output · $ / 1M tokens

DeepSeek V3.1 (Reasoning): Best: $1.68
Qwen3 VL 235B A22B (Reasoning): $4×2.4 relative to the lowest price among the compared models

Context window

DeepSeek V3.1 (Reasoning): 128K
Qwen3 VL 235B A22B (Reasoning): Best: 262K

Reasoning

DeepSeek V3.1 (Reasoning): Yes
Qwen3 VL 235B A22B (Reasoning): Yes

Open weights

DeepSeek V3.1 (Reasoning): Yes
Qwen3 VL 235B A22B (Reasoning): 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 V3.1 (Reasoning)13.5 · $0.855
Qwen3 VL 235B A22B (Reasoning)13.4 · $1.30