Model Comparator

Compare up to four models using the same criteria.

Mistral Medium 3.1
Mistral
Qwen3 Coder Next
Alibaba

Differences only

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

Model Comparator
Metrics	Mistral Medium 3.1 Mistral	Qwen3 Coder Next Alibaba
Intelligence	9.2	9.2
Coding	20.5	Best: 36.2
Math	38.3	—
Agentic	Best: 1.9	0.9
Speed	Best: 149 t/s	64.2 t/s
TTFT	2.23 s	Best: 1.15 s
Input · $ / 1M tokens	Best: $0.40	$0.50×1.3 relative to the lowest price among the compared models
Output · $ / 1M tokens	$2×1.7 relative to the lowest price among the compared models	Best: $1.20
Context window	128K	Best: 256K
Reasoning	No	No
Open weights	No	Yes
Cost / task	—	$0.781

Intelligence

Mistral Medium 3.1: 9.2
Qwen3 Coder Next: 9.2

Coding

Mistral Medium 3.1: 20.5
Qwen3 Coder Next: Best: 36.2

Math

Mistral Medium 3.1: 38.3
Qwen3 Coder Next: —

Agentic

Mistral Medium 3.1: Best: 1.9
Qwen3 Coder Next: 0.9

Speed

Mistral Medium 3.1: Best: 149 t/s
Qwen3 Coder Next: 64.2 t/s

TTFT

Mistral Medium 3.1: 2.23 s
Qwen3 Coder Next: Best: 1.15 s

Input · $ / 1M tokens

Mistral Medium 3.1: Best: $0.40
Qwen3 Coder Next: $0.50×1.3 relative to the lowest price among the compared models

Output · $ / 1M tokens

Mistral Medium 3.1: $2×1.7 relative to the lowest price among the compared models
Qwen3 Coder Next: Best: $1.20

Context window

Mistral Medium 3.1: 128K
Qwen3 Coder Next: Best: 256K

Reasoning

Mistral Medium 3.1: No
Qwen3 Coder Next: No

Open weights

Mistral Medium 3.1: No
Qwen3 Coder Next: Yes

Cost / task

Mistral Medium 3.1: —
Qwen3 Coder Next: $0.781

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.

Mistral Medium 3.19.2 · $405.87
Qwen3 Coder Next9.2 · $662.85