Compare / MiniMax-M2.1 vs MiniMax-M3

MiniMax-M2.1 vs MiniMax-M3

Which is cheaper, which is more capable, and which does better at each kind of work, from 13 results on 2 sources that measured both models.

MiniMaxMiniMax-M2.1 Released 23 Dec 2025 · Not on sale
MiniMaxMiniMax-M3 Released 1 Jun 2026 · $0.30 in · $1.20 out
MiniMax-M2.1 wins 0MiniMax-M3 wins 13

Of the 13 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).

MiniMax-M2.1 or MiniMax-M3? The short answer

Pick MiniMax-M3: it scores higher (Intelligence Index 29.2 against 20.9) at about the same price.

  • MiniMax-M3 scores higher on the Artificial Analysis Intelligence Index: 29.2 against 20.9.
  • MiniMax-M3 is newer: released 1 Jun 2026, against 23 Dec 2025 for MiniMax-M2.1.
  • On third-party benchmarks, on the results both models have: MiniMax-M3 does better for agents and tool use and reasoning and knowledge.

Head to head

20.9
Intelligence Index
29.2

Every fact side by side

MiniMax-M2.1MiniMax-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 Index20.929.2
Spring Prompt overall––
Output speed, tokens a second–146
Context window–1,048,576 tokens
Released23 Dec 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 132 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 97 of 188 45 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 101 of 170 67 of 169
Sticking to the factsSummarising without inventing things, and factual answers 109 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-M2.1MiniMax-M3
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 106 · 59 of 249 measured 20.9 29.2
GPQA Diamond% of questions, higher is better 97 · 14 of 232 measured 83.0% 92.9%
Humanity's Last Exam% of questions, higher is better 106 · 51 of 250 measured 23.2% 39.0%
OpenHands Index reported by OpenHands Index · 3 results
Average% resolved, higher is better 27 · 13 of 34 measured 41.2%openhands 57.2%openhands
Front end (SWE-Bench Multimodal)% resolved, higher is better 34 · 11 of 34 measured 16.2%openhands 36.8%openhands
Greenfield (Commit0)% resolved, higher is better 21 · 14 of 34 measured 18.8%openhands 25.0%openhands
Show all 13 results (7 more)
MeasureMiniMax-M2.1MiniMax-M3
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 56 · 3 of 195 measured 69.9% 82.9%
Long-context reasoning (AA-LCR)% of questions, higher is better 128 · 16 of 241 measured 67.7% 83.0%
Terminal-Bench Hard% of tasks, higher is better 69 · 29 of 190 measured 28.8% 42.4%
τ²-bench telecom% of tasks, higher is better 58 · 46 of 193 measured 85.4% 88.9%
OpenHands Index reported by OpenHands Index · 3 results
Information gathering (GAIA)% resolved, higher is better 27 · 15 of 34 measured 40.6%openhands 66.7%openhands
Issue resolution (SWE-Bench)% resolved, higher is better 27 · 9 of 34 measured 68.8%openhands 76.4%openhands
Testing (SWT-Bench)% resolved, higher is better 23 · 4 of 34 measured 61.4%openhands 81.1%openhands

Quick answers

Is MiniMax-M2.1 better than MiniMax-M3?

Pick MiniMax-M3: it scores higher (Intelligence Index 29.2 against 20.9) at about the same price.

Which is better for agents and tool use, MiniMax-M2.1 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 132 for MiniMax-M2.1.

Which is better for reasoning and knowledge, MiniMax-M2.1 or MiniMax-M3?

MiniMax-M3 ranks 45 of 188 models on sale for hard questions across science, maths and general knowledge, against 97 for MiniMax-M2.1.

Which is better for writing, MiniMax-M2.1 or MiniMax-M3?

MiniMax-M3 ranks 67 of 170 models on sale for what people prefer in blind comparisons, and judged writing quality, against 101 for MiniMax-M2.1.

Which is better for sticking to the facts, MiniMax-M2.1 or MiniMax-M3?

MiniMax-M3 ranks 91 of 140 models on sale for summarising without inventing things, and factual answers, against 109 for MiniMax-M2.1.

Run MiniMax-M2.1 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.