Model comparison
Mistral Small 3.2 vs MiniMax-Text-01
- Input
- $0.10
- Output
- $0.30
- Context
- 128K
- Released
- 2025-06-20
- Input
- $0.20 / 1M tokens
- Output
- $1.10 / 1M tokens
- Context
- 4M
- Released
- 2025-01-15
MiniMax-Text-01 scores higher on 4 of the 4 benchmarks both models report; Mistral Small 3.2 is cheaper on input tokens ($0.1 vs $0.2 per 1M, 2×); MiniMax-Text-01 has the larger context window (4M vs 128K).
Specs and pricing side by side
| Spec | Mistral Small 3.2 | MiniMax-Text-01 |
|---|---|---|
| Maker | Mistral AI | MiniMax |
| Released | 2025-06-20 | 2025-01-15 |
| Context window | 128K | 4M |
| Max output | not published | Not separately published |
| Input price | $0.10 | $0.20 / 1M tokens |
| Output price | $0.30 | $1.10 / 1M tokens |
| Parameters | 24B | 456B total / 45.9B active (MoE, 32 experts, Top-2 routing, 80 layers) |
| License | Apache 2.0 | MiniMax Model License Agreement (open weights, custom) |
| Weights | Open weights | Open weightssame |
| Modalities | Text, Vision | Text |
| Knowledge cutoff | October 2023 | Not officially stated |
Benchmarks both models report
| Benchmark | Mistral Small 3.2 | MiniMax-Text-01 |
|---|---|---|
| MMLU | 80.5% | 88.5% |
| MMLU Pro | 69.06% | 75.7% |
| MATH | 69.42% | 77.4% |
| GPQA Diamond | 46.13% | 54.4% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Mistral Small 3.2 if…
- Cost matters: input tokens cost 2× less ($0.1 vs $0.2 per 1M).
- You need Vision input, which MiniMax-Text-01 lacks.
- Your use case is: self-hosted chat assistants and internal copilots where data must stay on-premise.
Pick MiniMax-Text-01 if…
- You care about MMLU, MMLU Pro, MATH (it scores higher on 4 shared benchmarks).
- You need the longer context (4M vs 128K).
- Your use case is: long-document and whole-codebase analysis that needs hundreds of thousands to millions of tokens of context.
FAQ
Which is better, Mistral Small 3.2 or MiniMax-Text-01?
MiniMax-Text-01 scores higher on 4 of the 4 benchmarks both models report; Mistral Small 3.2 is cheaper on input tokens ($0.1 vs $0.2 per 1M, 2×); MiniMax-Text-01 has the larger context window (4M vs 128K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Mistral Small 3.2?
Mistral Small 3.2: $0.10 input, $0.30 output. MiniMax-Text-01: $0.20 / 1M tokens input, $1.10 / 1M tokens output (list API prices as published by each maker).
What are the context windows of Mistral Small 3.2 and MiniMax-Text-01?
Mistral Small 3.2 offers 128K; MiniMax-Text-01 offers 4M with up to Not separately published output.
Is Mistral Small 3.2 newer than MiniMax-Text-01?
Mistral Small 3.2 was released 2025-06-20; MiniMax-Text-01 was released 2025-01-15.
Go deeper
- Mistral Small 3.2: full specs, pricing and benchmarks
- MiniMax-Text-01: full specs, pricing and benchmarks
- mistral small 3 2 vs mistral small 3 1
- mistral small 4 vs mistral small 3 2
- minimax text 01 vs llama 3 3
- mistral small 3 2 vs gemini 2 0 flash
- gemma 3 vs minimax text 01
- deepseek r1 vs minimax text 01
- All model comparisons