Model Comparator

Compare up to four models using the same criteria.

Qwen3.5 2B (Reasoning)
Alibaba
Llama 3.1 Instruct 8B
Meta

Differences only

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

Model Comparator
Metrics	Qwen3.5 2B (Reasoning) Alibaba	Llama 3.1 Instruct 8B Meta
Intelligence	6.9	6.9
Coding	2.9	Best: 5.4
Math	—	4.3
Speed	—	139 t/s
TTFT	—	0.9 s
Input · $ / 1M tokens	—	$0.035
Output · $ / 1M tokens	—	$0.065
Context window	Best: 262K	128K
Reasoning	Yes	No
Open weights	Yes	Yes

Intelligence

Qwen3.5 2B (Reasoning): 6.9
Llama 3.1 Instruct 8B: 6.9

Coding

Qwen3.5 2B (Reasoning): 2.9
Llama 3.1 Instruct 8B: Best: 5.4

Math

Qwen3.5 2B (Reasoning): —
Llama 3.1 Instruct 8B: 4.3

Speed

Qwen3.5 2B (Reasoning): —
Llama 3.1 Instruct 8B: 139 t/s

TTFT

Qwen3.5 2B (Reasoning): —
Llama 3.1 Instruct 8B: 0.9 s

Input · $ / 1M tokens

Qwen3.5 2B (Reasoning): —
Llama 3.1 Instruct 8B: $0.035

Output · $ / 1M tokens

Qwen3.5 2B (Reasoning): —
Llama 3.1 Instruct 8B: $0.065

Context window

Qwen3.5 2B (Reasoning): Best: 262K
Llama 3.1 Instruct 8B: 128K

Reasoning

Qwen3.5 2B (Reasoning): Yes
Llama 3.1 Instruct 8B: No

Open weights

Qwen3.5 2B (Reasoning): Yes
Llama 3.1 Instruct 8B: 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 3.1 Instruct 8B6.9 · $0.043

Not plotted for lack of data on these axes: Qwen3.5 2B (Reasoning).