Model Comparison

DeepSeek-V3.2 (Thinking) vs MiniMax M2

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks. DeepSeek-V3.2 (Thinking) is 1.7x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

9 benchmarks

DeepSeek-V3.2 (Thinking) outperforms in 9 benchmarks (AIME 2025, BrowseComp, BrowseComp-zh, GPQA, Humanity's Last Exam, LiveCodeBench, MMLU-Pro, SWE-bench Multilingual, SWE-Bench Verified), while MiniMax M2 is better at 0 benchmarks.

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks.

Fri May 01 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

DeepSeek-V3.2 (Thinking) costs less

For input processing, DeepSeek-V3.2 (Thinking) ($0.28/1M tokens) is 1.1x cheaper than MiniMax M2 ($0.30/1M tokens).

For output processing, DeepSeek-V3.2 (Thinking) ($0.42/1M tokens) is 2.9x cheaper than MiniMax M2 ($1.20/1M tokens).

In conclusion, MiniMax M2 is more expensive than DeepSeek-V3.2 (Thinking).*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Fri May 01 2026 • llm-stats.com
DeepSeek
DeepSeek-V3.2 (Thinking)
Input tokens$0.28
Output tokens$0.42
Best providerDeepSeek
MiniMax
MiniMax M2
Input tokens$0.30
Output tokens$1.20
Best providerMiniMax
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

455.0B diff

DeepSeek-V3.2 (Thinking) has 455.0B more parameters than MiniMax M2, making it 197.8% larger.

DeepSeek
DeepSeek-V3.2 (Thinking)
685.0Bparameters
MiniMax
MiniMax M2
230.0Bparameters
685.0B
DeepSeek-V3.2 (Thinking)
230.0B
MiniMax M2

Context Window

Maximum input and output token capacity

MiniMax M2 accepts 1,000,000 input tokens compared to DeepSeek-V3.2 (Thinking)'s 131,072 tokens. MiniMax M2 can generate longer responses up to 1,000,000 tokens, while DeepSeek-V3.2 (Thinking) is limited to 65,536 tokens.

DeepSeek
DeepSeek-V3.2 (Thinking)
Input131,072 tokens
Output65,536 tokens
MiniMax
MiniMax M2
Input1,000,000 tokens
Output1,000,000 tokens
Fri May 01 2026 • llm-stats.com

License

Usage and distribution terms

Both models are licensed under MIT.

Both models share the same licensing terms, providing consistent usage rights.

DeepSeek-V3.2 (Thinking)

MIT

Open weights

MiniMax M2

MIT

Open weights

Release Timeline

When each model was launched

DeepSeek-V3.2 (Thinking) was released on 2025-12-01, while MiniMax M2 was released on 2025-10-27.

DeepSeek-V3.2 (Thinking) is 1 month newer than MiniMax M2.

DeepSeek-V3.2 (Thinking)

Dec 1, 2025

5 months ago

1mo newer
MiniMax M2

Oct 27, 2025

6 months ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

DeepSeek-V3.2 (Thinking) is available from DeepSeek. MiniMax M2 is available from MiniMax, Novita.

DeepSeek-V3.2 (Thinking)

deepseek logo
DeepSeek
Input Price:Input: $0.28/1MOutput Price:Output: $0.42/1M

MiniMax M2

minimax logo
MiniMax
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M
novita logo
Novita
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

DeepSeek
Less expensive input tokens
Less expensive output tokens
Higher AIME 2025 score (93.1% vs 78.0%)
Higher BrowseComp score (51.4% vs 44.0%)
Higher BrowseComp-zh score (65.0% vs 48.5%)
Higher GPQA score (82.4% vs 78.0%)
Higher Humanity's Last Exam score (25.1% vs 12.5%)
Higher LiveCodeBench score (83.3% vs 83.0%)
Higher MMLU-Pro score (85.0% vs 82.0%)
Higher SWE-bench Multilingual score (70.2% vs 56.5%)
Higher SWE-Bench Verified score (73.1% vs 69.4%)
MiniMax
Larger context window (1,000,000 tokens)

Detailed Comparison

AI Model Comparison Table
Feature
DeepSeek
DeepSeek-V3.2 (Thinking)
MiniMax
MiniMax M2

FAQ

Common questions about DeepSeek-V3.2 (Thinking) vs MiniMax M2

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks. DeepSeek-V3.2 (Thinking) is made by DeepSeek and MiniMax M2 is made by MiniMax. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
DeepSeek-V3.2 (Thinking) scores AIME 2025: 93.1%, HMMT 2025: 90.2%, MMLU-Pro: 85.0%, LiveCodeBench: 83.3%, GPQA: 82.4%. MiniMax M2 scores Tau2 Telecom: 87.0%, LiveCodeBench: 83.0%, MMLU-Pro: 82.0%, AIME 2025: 78.0%, GPQA: 78.0%.
DeepSeek-V3.2 (Thinking) is 1.1x cheaper for input tokens. DeepSeek-V3.2 (Thinking) costs $0.28/M input and $0.42/M output via deepseek. MiniMax M2 costs $0.30/M input and $1.20/M output via minimax.
DeepSeek-V3.2 (Thinking) supports 131K tokens and MiniMax M2 supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (131K vs 1.0M), input pricing ($0.28 vs $0.30/M). See the full comparison above for benchmark-by-benchmark results.
DeepSeek-V3.2 (Thinking) is developed by DeepSeek and MiniMax M2 is developed by MiniMax.