Model comparison
MiniMax-M2 vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 37.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
MiniMaxSummary
- They share 18 benchmarks with published results for both. MiniMax-M2 scores higher in 1 category and MiniMax-M2.1 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 53.0.
- The biggest single-benchmark swing is Terminal-Bench: 30% for MiniMax-M2 and 36.6% for MiniMax-M2.1.
- Both cost about the same: $0.30 input and $1.20 output per million tokens.
Side by side
| MiniMax-M2 | MiniMax-M2.1 | |
|---|---|---|
| Provider | MiniMax | MiniMax |
| Noometry Index | 37.4 | 38.9 |
| Released | 2025-10-27 | 2025-12-23 |
| Weights | Open | Open |
| Context window | 205K | 205K |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.30 | $0.30 |
| Output $ / M tokens | $1.20 | $1.20 |
| Results tracked | 21 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
MiniMax-M2: 39.3 (#159), MiniMax-M2.1: 40.4 (#143)
| Benchmark | MiniMax-M2 | MiniMax-M2.1 |
|---|---|---|
| LMArena WebDev | 1297 | 1384 |
| LMArena Coding | 1370 | 1421 |
| SWE-bench Verified (bash only) | 61% | — |
| ALE-Bench | — | 623.83 |
Agentic & Tool Use MiniMax-M2.1 leads
MiniMax-M2: 25.1 (#109), MiniMax-M2.1: 27.9 (#98)
| Benchmark | MiniMax-M2 | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | 30% | 36.6% |
| Vending-Bench 2 | 160.6 | — |
Reasoning MiniMax-M2 leads
MiniMax-M2: 19.4 (#258), MiniMax-M2.1: 16.6 (#302)
| Benchmark | MiniMax-M2 | MiniMax-M2.1 |
|---|---|---|
| NYT Connections (extended) | 14.8% | 11.2% |
| LMArena Hard Prompts | 1357 | 1411 |
| Kagi LLM Benchmark | 57.8% | — |
Math MiniMax-M2.1 leads
MiniMax-M2: 37.3 (#160), MiniMax-M2.1: 38.3 (#138)
| Benchmark | MiniMax-M2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1352 | 1397 |
Knowledge MiniMax-M2.1 leads
MiniMax-M2: 37.0 (#163), MiniMax-M2.1: 38.3 (#147)
| Benchmark | MiniMax-M2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1337 | 1431 |
| Vectara Hallucination Rate | — | 11.8% |
Multilingual MiniMax-M2.1 leads
MiniMax-M2: 45.3 (#171), MiniMax-M2.1: 50.0 (#128)
| Benchmark | MiniMax-M2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1313 | 1378 |
| LMArena Chinese | 1366 | 1430 |
| LMArena French | 1335 | 1404 |
| LMArena German | 1355 | 1381 |
| LMArena Russian | 1331 | 1387 |
| LMArena Spanish | 1326 | 1397 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1298 |
Instruction Following MiniMax-M2.1 leads
MiniMax-M2: 70.2 (#166), MiniMax-M2.1: 73.8 (#112)
| Benchmark | MiniMax-M2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1328 | 1400 |
Long Context MiniMax-M2.1 leads
MiniMax-M2: 40.5 (#153), MiniMax-M2.1: 43.2 (#101)
| Benchmark | MiniMax-M2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1331 | 1416 |
Writing & Preference MiniMax-M2.1 leads
MiniMax-M2: 53.0 (#162), MiniMax-M2.1: 58.3 (#120)
| Benchmark | MiniMax-M2 | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1340 | 1392 |
| LMArena Creative Writing | 1286 | 1361 |
| LMArena Multi-Turn | 1361 | 1396 |
Frequently asked questions
Is MiniMax-M2 better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 37.4 on the Noometry Index.
Which is cheaper, MiniMax-M2 or MiniMax-M2.1?
MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.
Is MiniMax-M2 or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 39.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 205K tokens.
How many benchmarks do MiniMax-M2 and MiniMax-M2.1 share?
18 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and MiniMax-M2.1 has 22.