Kimi K2 Thinking vs Qwen3-235B-A22B

Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.

Kimi K2 Thinking

Moonshot AI · Nov 2025

67.6

A trillion-parameter open reasoning agent that can chain 200–300 tool calls — the open-weights agentic standout of late 2025.

Qwen3-235B-A22B

Alibaba (Qwen) · Jul 2025

69.0

The most popular open general-purpose Qwen: 235B MoE with hybrid thinking, a staple of the 2025 open-source ecosystem.

The verdict

Kimi K2 Thinking wins 4 of the 4 benchmarks these models share, against 0 for Qwen3-235B-A22B. Qwen3-235B-A22B is about 2.8x cheaper per blended million tokens (3:1 input:output mix).

Benchmark head-to-head 40

GPQA Diamond
84.5%81.1%
Kimi K2 ThinkingQwen3-235B-A22B
AIME 2025
~94.5%92.3%
Kimi K2 ThinkingQwen3-235B-A22B
HLE
23.9%~18.2%
Kimi K2 ThinkingQwen3-235B-A22B
MMLU-Pro
~84.6%84.4%
Kimi K2 ThinkingQwen3-235B-A22B

Specs & pricing

Kimi K2 ThinkingQwen3-235B-A22B
modhub Index67.669.0
Input price / 1M$0.6$0.22
Output price / 1M$2.5$0.88
Context window262K262K
Max output33K
Open weightsyes (Modified MIT)yes (Apache 2.0)
Reasoning modelyesyes
Multimodal inputtexttext
Knowledge cutoffApr 2025Apr 2025
ReleasedNov 2025Jul 2025
Example monthly cost*$9.75$3.52

* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.

Frequently asked questions

Which is better, Kimi K2 Thinking or Qwen3-235B-A22B?
Kimi K2 Thinking wins 4 of the 4 benchmarks these models share, against 0 for Qwen3-235B-A22B. Qwen3-235B-A22B is about 2.8x cheaper per blended million tokens (3:1 input:output mix).
Which is cheaper, Kimi K2 Thinking or Qwen3-235B-A22B?
Kimi K2 Thinking costs $0.6/$2.5 per million input/output tokens, while Qwen3-235B-A22B costs $0.22/$0.88. For a typical workload of 10M input and 1.5M output tokens per month, that's $9.75 versus $3.52.
Which model is better for coding, Kimi K2 Thinking or Qwen3-235B-A22B?
We don't yet track SWE-bench Verified results for both models; check their individual pages for coding-related scores.

More comparisons