Model Comparator

Compare up to four models using the same criteria.

Qwen3.5 4B (Non-reasoning)
Alibaba
Mercury 2
Inception

Differences only

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

Model Comparator
Metrics	Qwen3.5 4B (Non-reasoning) Alibaba	Mercury 2 Inception
Intelligence	10.8	10.8
Coding	20.3	Best: 31.1
Agentic	—	1.6
Speed	13.1 t/s	Best: 460 t/s
TTFT	Best: 1 s	6.17 s
Input · $ / 1M tokens	Best: $0.030	$0.25×8.3 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.15	$0.75×5 relative to the lowest price among the compared models
Context window	Best: 262K	128K
Reasoning	No	Yes
Open weights	Yes	No
Cost / task	—	$0.0386

Intelligence

Qwen3.5 4B (Non-reasoning): 10.8
Mercury 2: 10.8

Coding

Qwen3.5 4B (Non-reasoning): 20.3
Mercury 2: Best: 31.1

Agentic

Qwen3.5 4B (Non-reasoning): —
Mercury 2: 1.6

Speed

Qwen3.5 4B (Non-reasoning): 13.1 t/s
Mercury 2: Best: 460 t/s

TTFT

Qwen3.5 4B (Non-reasoning): Best: 1 s
Mercury 2: 6.17 s

Input · $ / 1M tokens

Qwen3.5 4B (Non-reasoning): Best: $0.030
Mercury 2: $0.25×8.3 relative to the lowest price among the compared models

Output · $ / 1M tokens

Qwen3.5 4B (Non-reasoning): Best: $0.15
Mercury 2: $0.75×5 relative to the lowest price among the compared models

Context window

Qwen3.5 4B (Non-reasoning): Best: 262K
Mercury 2: 128K

Reasoning

Qwen3.5 4B (Non-reasoning): No
Mercury 2: Yes

Open weights

Qwen3.5 4B (Non-reasoning): Yes
Mercury 2: No

Cost / task

Qwen3.5 4B (Non-reasoning): —
Mercury 2: $0.0386

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.

Qwen3.5 4B (Non-reasoning)10.8 · $0.060
Mercury 210.8 · $0.375