Compare / MiniMax M2 vs MiniMax M3
MiniMax M2 vs MiniMax M3
Which is cheaper, which is more capable, and which does better at each kind of work, from 15 results on 3 sources that measured both models.
MiniMax M2 or MiniMax M3? The short answer
- MiniMax M3 scores higher on the Artificial Analysis Intelligence Index: 29.2 against 18.6.
- On our business benchmarks, MiniMax M3 ranks higher for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
At a glance
| MiniMax M2 | MiniMax M3 | |
|---|---|---|
| Price per million tokens | $0.30 in · $1.20 out | $0.30 in · $1.20 out |
| Blended (3 in : 1 out) | $0.52 | $0.52 |
| Cheapest host, blended | $0.45 (Minimax, FP8) | $0.41 (CoreWeave, FP4) |
| Intelligence Index | 18.6 | 29.2 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | 81 |
| Context window | 204,800 tokens | 1,048,576 tokens |
| Weights | Open | Open |
| Developer based in | China | China |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | MiniMax M2 | MiniMax M3 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 149 of 161 | 71 of 161 |
| Professional workReal tasks from banking, consulting and law, business documents and freelance projects | not measured | 39 of 51 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 107 of 195 | 36 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 167 of 187 | 61 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 150 of 153 | 94 of 153 |
Every shared result
| Benchmark | Metric | MiniMax M2 | MiniMax M3 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,360 | 1,434 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,348 | 1,450 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,285 | 1,406 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,350 | 1,471 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,334 | 1,435 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,343 | 1,440 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,298 | 1,422 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 18.6 | 29.2 |
| Artificial Analysisreported | GPQA Diamond% of questions | 77.7% | 92.9% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 13.7% | 39.0% |
| Artificial Analysisreported | IFBench% of instructions | 72.3% | 82.9% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 64.3% | 83.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 25.8% | 42.4% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 86.8% | 88.9% |
| Vending-Bench 2reported | Money after a yearUS dollars | $160.60 | $2,157.77 |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.
Quick answers
Is MiniMax M2 better than MiniMax M3?
It depends on the task. Among models available today, on our benchmarks and licensed sources, MiniMax M3 ranks higher for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
Run MiniMax M2 and MiniMax M3 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.