Kimi K2 0905 vs Qwen3 235B A22B
Kimi K2 0905 significantly outperforms across most benchmarks. Qwen3 235B A22B is 10.7x cheaper per token.
Moonshot AI · Alibaba Cloud / Qwen Team · Updated for 2026
Which is better?
Kimi K2 0905 outperforms in 4 benchmarks (GPQA, MATH, MMLU, MMLU-Pro), while Qwen3 235B A22B is better at 1 benchmark (AIME 2024). Kimi K2 0905 significantly outperforms across most benchmarks.
On price, Qwen3 235B A22B is roughly 10.7x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Kimi K2 0905 also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.
Based on current benchmark, pricing, and model metadata for 2026.
Choose Kimi K2 0905
- you want the strongest raw capability — it leads on 4 of 5 shared benchmarks
- you process long inputs — it offers a 262,144 token context window
- you want the most recent training data — it shipped Sep 2025
Choose Qwen3 235B A22B
- cost matters — it's about 10.7x cheaper per token
- you need open weights you can self-host or fine-tune
At a glance
The differences that matter most.
Performance Benchmarks
Comparative analysis across standard metrics
Kimi K2 0905 outperforms in 4 benchmarks (GPQA, MATH, MMLU, MMLU-Pro), while Qwen3 235B A22B is better at 1 benchmark (AIME 2024).
Kimi K2 0905 significantly outperforms across most benchmarks.
Arena Performance
Playground indexes and blind preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Kimi K2 0905 ($0.60/1M tokens) is 6.0x more expensive than Qwen3 235B A22B ($0.10/1M tokens).
For output processing, Kimi K2 0905 ($2.50/1M tokens) is 25.0x more expensive than Qwen3 235B A22B ($0.10/1M tokens).
In conclusion, Kimi K2 0905 is more expensive than Qwen3 235B A22B.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
Kimi K2 0905 has 765.0B more parameters than Qwen3 235B A22B, making it 325.5% larger.
Context Window
Maximum input and output token capacity
Kimi K2 0905 accepts 262,144 input tokens compared to Qwen3 235B A22B's 128,000 tokens. Kimi K2 0905 can generate longer responses up to 262,144 tokens, while Qwen3 235B A22B is limited to 128,000 tokens.
License
Usage and distribution terms
Kimi K2 0905 is licensed under a proprietary license, while Qwen3 235B A22B uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
Proprietary
Closed source
Apache 2.0
Open weights
Release Timeline
When each model was launched
Kimi K2 0905 was released on 2025-09-05, while Qwen3 235B A22B was released on 2025-04-29.
Kimi K2 0905 is 4 months newer than Qwen3 235B A22B.
Sep 5, 2025
11 months ago
4mo newerApr 29, 2025
1.3 years ago
Knowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Kimi K2 0905 is available from Novita. Qwen3 235B A22B is available from Fireworks, DeepInfra, Novita, Together.
Kimi K2 0905
Qwen3 235B A22B
Outputs Comparison
Judge for yourself.
Run your own prompts against Kimi K2 0905 and Qwen3 235B A22B side-by-side, then vote on the output you prefer.
FAQ
Common questions about Kimi K2 0905 vs Qwen3 235B A22B.