Qwen3 235B A22B 2507 (Reasoning) vs Kimi K2 Thinking
Comparing 2 AI models · 6 benchmarks · Alibaba, Moonshot AI
Most Affordable
Mo
Kimi K2 Thinking
$0.60/1M
Highest Intelligence
Mo
Kimi K2 Thinking
83.8% GPQA
Best for Coding
Mo
Kimi K2 Thinking
52.2 Coding Index
Price Difference
1.2x
input cost range
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Benchmark Winners
6 tests
Al
Qwen3 235B A22B 2507 (Reasoning)
1
- MATH 500
Mo
Kimi K2 Thinking
5
- GPQA
- MMLU Pro
- HLE
- LiveCodeBench
- AIME 2025
| Metric | Al Qwen3 235B A22B 2507 (Reasoning) | Mo Kimi K2 Thinking |
|---|---|---|
| Pricing Per 1M tokens | ||
| Input Cost | $0.70/1M | $0.60/1M |
| Output Cost | $8.40/1M | $2.50/1M |
| Blended Cost 3:1 input/output ratio | $2.63/1M | $1.07/1M |
| Specifications | ||
| Organization Model creator | Alibaba | Moonshot AI |
| Release Date Launch date | Jul 25, 2025 | Nov 6, 2025 |
| Performance & Speed | ||
| Throughput Output speed | 82.6 tok/s | 78.7 tok/s |
| Time to First Token (TTFT) Initial response delay | 1136ms | 816ms |
| Latency Time to first answer token | ||