Model Comparator

Compare up to four models using the same criteria.

Kimi K2
Moonshot AI
Qwen3 235B A22B 2507 (Reasoning)
Alibaba

Differences only

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

Model Comparator
Metrics	Kimi K2 Moonshot AI	Qwen3 235B A22B 2507 (Reasoning) Alibaba
Intelligence	12.7	12.7
Coding	—	22.1
Math	57	Best: 91
Agentic	—	1.3
Speed	55.1 t/s	Best: 85.4 t/s
TTFT	1.49 s	Best: 0.8 s
Input · $ / 1M tokens	$0.57×2.5 relative to the lowest price among the compared models	Best: $0.23
Output · $ / 1M tokens	$2.30	$2.30
Context window	128K	Best: 256K
Reasoning	No	Yes
Open weights	Yes	Yes
Cost / task	—	$0.0806

Intelligence

Kimi K2: 12.7
Qwen3 235B A22B 2507 (Reasoning): 12.7

Coding

Kimi K2: —
Qwen3 235B A22B 2507 (Reasoning): 22.1

Math

Kimi K2: 57
Qwen3 235B A22B 2507 (Reasoning): Best: 91

Agentic

Kimi K2: —
Qwen3 235B A22B 2507 (Reasoning): 1.3

Speed

Kimi K2: 55.1 t/s
Qwen3 235B A22B 2507 (Reasoning): Best: 85.4 t/s

TTFT

Kimi K2: 1.49 s
Qwen3 235B A22B 2507 (Reasoning): Best: 0.8 s

Input · $ / 1M tokens

Kimi K2: $0.57×2.5 relative to the lowest price among the compared models
Qwen3 235B A22B 2507 (Reasoning): Best: $0.23

Output · $ / 1M tokens

Kimi K2: $2.30
Qwen3 235B A22B 2507 (Reasoning): $2.30

Context window

Kimi K2: 128K
Qwen3 235B A22B 2507 (Reasoning): Best: 256K

Reasoning

Kimi K2: No
Qwen3 235B A22B 2507 (Reasoning): Yes

Open weights

Kimi K2: Yes
Qwen3 235B A22B 2507 (Reasoning): Yes

Cost / task

Kimi K2: —
Qwen3 235B A22B 2507 (Reasoning): $0.0806

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.

Kimi K212.7 · $1.00
Qwen3 235B A22B 2507 (Reasoning)12.7 · $0.747