Model Comparator

Compare up to four models using the same criteria.

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

Differences only

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

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

Intelligence

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

Coding

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

Math

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

Agentic

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

Speed

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

TTFT

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

Input · $ / 1M tokens

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

Output · $ / 1M tokens

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

Context window

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

Reasoning

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

Open weights

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

Cost / task

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

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