MiniMax M2 vs Qwen3-235B-A22B
Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.
MiniMax M2
68.9MiniMax · Oct 2025
A 10B-active MoE tuned purely for agents and code — striking capability-per-active-parameter at rock-bottom prices.
Qwen3-235B-A22B
69.0Alibaba (Qwen) · Jul 2025
The most popular open general-purpose Qwen: 235B MoE with hybrid thinking, a staple of the 2025 open-source ecosystem.
The verdict
Qwen3-235B-A22B wins 2 of the 2 benchmarks these models share, against 0 for MiniMax M2. Qwen3-235B-A22B is about 1.4x cheaper per blended million tokens (3:1 input:output mix). Qwen3-235B-A22B also takes 262K of context versus 205K for MiniMax M2.
Benchmark head-to-head 0–2
Specs & pricing
| MiniMax M2 | Qwen3-235B-A22B | |
|---|---|---|
| modhub Index | 68.9 | 69.0 |
| Input price / 1M | $0.3 | $0.22 |
| Output price / 1M | $1.2 | $0.88 |
| Context window | 205K | 262K |
| Max output | — | 33K |
| Open weights | yes (MIT) | yes (Apache 2.0) |
| Reasoning model | yes | yes |
| Multimodal input | text | text |
| Knowledge cutoff | Jun 2025 | Apr 2025 |
| Released | Oct 2025 | Jul 2025 |
| Example monthly cost* | $4.80 | $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, MiniMax M2 or Qwen3-235B-A22B?
- Qwen3-235B-A22B wins 2 of the 2 benchmarks these models share, against 0 for MiniMax M2. Qwen3-235B-A22B is about 1.4x cheaper per blended million tokens (3:1 input:output mix). Qwen3-235B-A22B also takes 262K of context versus 205K for MiniMax M2.
- Which is cheaper, MiniMax M2 or Qwen3-235B-A22B?
- MiniMax M2 costs $0.3/$1.2 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 $4.80 versus $3.52.
- Which model is better for coding, MiniMax M2 or Qwen3-235B-A22B?
- We don't yet track SWE-bench Verified results for both models; check their individual pages for coding-related scores.