Model Comparator

Compare up to four models using the same criteria.

Qwen3.6 35B A3B (Non-reasoning)
Alibaba
Kimi K2 0905
Moonshot AI

Differences only

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

Model Comparator
Metrics	Qwen3.6 35B A3B (Non-reasoning) Alibaba	Kimi K2 0905 Moonshot AI
Intelligence	15.2	Best: 15.3
Coding	28.1	—
Math	—	57.3
Speed	Best: 135 t/s	56.1 t/s
TTFT	2.04 s	Best: 1.26 s
Input · $ / 1M tokens	Best: $0.375	$0.60×1.6 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $2.25	$2.50×1.1 relative to the lowest price among the compared models
Context window	Best: 262K	256K
Reasoning	No	No
Open weights	Yes	Yes

Intelligence

Qwen3.6 35B A3B (Non-reasoning): 15.2
Kimi K2 0905: Best: 15.3

Coding

Qwen3.6 35B A3B (Non-reasoning): 28.1
Kimi K2 0905: —

Math

Qwen3.6 35B A3B (Non-reasoning): —
Kimi K2 0905: 57.3

Speed

Qwen3.6 35B A3B (Non-reasoning): Best: 135 t/s
Kimi K2 0905: 56.1 t/s

TTFT

Qwen3.6 35B A3B (Non-reasoning): 2.04 s
Kimi K2 0905: Best: 1.26 s

Input · $ / 1M tokens

Qwen3.6 35B A3B (Non-reasoning): Best: $0.375
Kimi K2 0905: $0.60×1.6 relative to the lowest price among the compared models

Output · $ / 1M tokens

Qwen3.6 35B A3B (Non-reasoning): Best: $2.25
Kimi K2 0905: $2.50×1.1 relative to the lowest price among the compared models

Context window

Qwen3.6 35B A3B (Non-reasoning): Best: 262K
Kimi K2 0905: 256K

Reasoning

Qwen3.6 35B A3B (Non-reasoning): No
Kimi K2 0905: No

Open weights

Qwen3.6 35B A3B (Non-reasoning): Yes
Kimi K2 0905: 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.

Qwen3.6 35B A3B (Non-reasoning)15.2 · $0.844
Kimi K2 090515.3 · $1.08