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.

MiniMaxMiniMax-M2 Released 27 Oct 2025 · Not on sale
MiniMaxMiniMax-M3 Released 1 Jun 2026 · $0.30 in · $1.20 out
MiniMax-M2 wins 0MiniMax-M3 wins 15

Of the 15 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331).

MiniMax-M2 or MiniMax-M3? The short answer

Pick MiniMax-M3: it scores higher (Intelligence Index 29.2 against 18.6) at about the same price.

  • MiniMax-M3 scores higher on the Artificial Analysis Intelligence Index: 29.2 against 18.6.
  • MiniMax-M3 is newer: released 1 Jun 2026, against 27 Oct 2025 for MiniMax-M2.
  • On third-party benchmarks, on the results both models have: MiniMax-M3 does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.

Head to head

18.6
Intelligence Index
29.2

Every fact side by side

MiniMax-M2MiniMax-M3
Price per million tokensNot on sale$0.30 in · $1.20 out
Blended (3 in : 1 out)–$0.52
Cheapest host, blended–$0.41 (CoreWeave, FP4)
Cached input, per million–$0.060 cached input
Intelligence Index18.629.2
Spring Prompt overall––
Output speed, tokens a second–146
Context window–1,048,576 tokens
Released27 Oct 20251 Jun 2026 (newer)
WeightsClosedOpen
Developer based inChinaChina

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 the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 150 of 160 79 of 159
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 116 of 188 45 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 152 of 170 67 of 169
Sticking to the factsSummarising without inventing things, and factual answers 137 of 140 91 of 139

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureMiniMax-M2MiniMax-M3
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 199 · 84 of 387 measured 1,343 1,440
Overall · Text factualityArena rating, higher is better 156 · 89 of 163 measured 1,360 1,434
Business, management and finance · TextArena rating, higher is better 196 · 68 of 380 measured 1,348 1,448
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 116 · 59 of 249 measured 18.6 29.2
GPQA Diamond% of questions, higher is better 123 · 14 of 232 measured 77.7% 92.9%
Humanity's Last Exam% of questions, higher is better 141 · 51 of 250 measured 13.7% 39.0%
Vending-Bench 2 reported by Vending-Bench 2 · 1 result
Money after a yearUS dollars, higher is better 51 · 40 of 58 measured $160.60 $2,158
Show all 15 results (8 more)
MeasureMiniMax-M2MiniMax-M3
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 229 · 84 of 385 measured 1,285 1,406
Expert prompts · TextArena rating, higher is better 194 · 80 of 338 measured 1,350 1,470
Instruction following · TextArena rating, higher is better 193 · 76 of 387 measured 1,334 1,434
Writing, literature and language · TextArena rating, higher is better 232 · 77 of 386 measured 1,299 1,422
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 41 · 3 of 195 measured 72.3% 82.9%
Long-context reasoning (AA-LCR)% of questions, higher is better 138 · 16 of 241 measured 64.3% 83.0%
Terminal-Bench Hard% of tasks, higher is better 77 · 29 of 190 measured 25.8% 42.4%
τ²-bench telecom% of tasks, higher is better 51 · 46 of 193 measured 86.8% 88.9%

Quick answers

Is MiniMax-M2 better than MiniMax-M3?

Pick MiniMax-M3: it scores higher (Intelligence Index 29.2 against 18.6) at about the same price.

Which is better for agents and tool use, MiniMax-M2 or MiniMax-M3?

MiniMax-M3 ranks 79 of 160 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 150 for MiniMax-M2.

Which is better for reasoning and knowledge, MiniMax-M2 or MiniMax-M3?

MiniMax-M3 ranks 45 of 188 models on sale for hard questions across science, maths and general knowledge, against 116 for MiniMax-M2.

Which is better for writing, MiniMax-M2 or MiniMax-M3?

MiniMax-M3 ranks 67 of 170 models on sale for what people prefer in blind comparisons, and judged writing quality, against 152 for MiniMax-M2.

Which is better for sticking to the facts, MiniMax-M2 or MiniMax-M3?

MiniMax-M3 ranks 91 of 140 models on sale for summarising without inventing things, and factual answers, against 137 for MiniMax-M2.

Run MiniMax-M2 and MiniMax-M3 on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.