Model comparison
MiniMax-M2 vs o1-pro
MiniMax-M2 is the stronger model overall, scoring 37.4 to 31.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
MiniMaxSummary
- The widest gap is in knowledge, where MiniMax-M2 leads 37.0 to 29.7.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $150 / $600 for o1-pro.
- MiniMax-M2 accepts more context: 205K tokens versus 200K.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2 | o1-pro | |
|---|---|---|
| Provider | MiniMax | OpenAI |
| Noometry Index | 37.4 | 31.5 |
| Released | 2025-10-27 | 2025-03-19 |
| Weights | Open | Proprietary |
| Context window | 205K | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $0.30 | $150 |
| Output $ / M tokens | $1.20 | $600 |
| Results tracked | 21 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiniMax-M2: 39.3 (#159), o1-pro: —
| Benchmark | MiniMax-M2 | o1-pro |
|---|---|---|
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
| LMArena Coding | 1370 | — |
Agentic & Tool Use Not comparable
MiniMax-M2: 25.1 (#109), o1-pro: —
| Benchmark | MiniMax-M2 | o1-pro |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |
Reasoning o1-pro leads
MiniMax-M2: 19.4 (#258), o1-pro: 20.4 (#239)
| Benchmark | MiniMax-M2 | o1-pro |
|---|---|---|
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |
| ARC-AGI-1 | — | 23.3% |
| EnigmaEval | — | 6.1% |
| LMArena Hard Prompts | 1357 | — |
Math Not comparable
MiniMax-M2: 37.3 (#160), o1-pro: —
| Benchmark | MiniMax-M2 | o1-pro |
|---|---|---|
| LMArena Math | 1352 | — |
Knowledge MiniMax-M2 leads
MiniMax-M2: 37.0 (#163), o1-pro: 29.7 (#234)
| Benchmark | MiniMax-M2 | o1-pro |
|---|---|---|
| Humanity's Last Exam | — | 8.1% |
| LMArena Expert | 1337 | — |
Multilingual Not comparable
MiniMax-M2: 45.3 (#171), o1-pro: —
| Benchmark | MiniMax-M2 | o1-pro |
|---|---|---|
| LMArena Non-English | 1313 | — |
| LMArena Chinese | 1366 | — |
| LMArena French | 1335 | — |
| LMArena German | 1355 | — |
| LMArena Russian | 1331 | — |
| LMArena Spanish | 1326 | — |
Instruction Following Not comparable
MiniMax-M2: 70.2 (#166), o1-pro: —
| Benchmark | MiniMax-M2 | o1-pro |
|---|---|---|
| LMArena Instruction Following | 1328 | — |
Long Context Not comparable
MiniMax-M2: 40.5 (#153), o1-pro: —
| Benchmark | MiniMax-M2 | o1-pro |
|---|---|---|
| LMArena Longer Query | 1331 | — |
Writing & Preference Not comparable
MiniMax-M2: 53.0 (#162), o1-pro: —
| Benchmark | MiniMax-M2 | o1-pro |
|---|---|---|
| LMArena Text | 1340 | — |
| LMArena Creative Writing | 1286 | — |
| LMArena Multi-Turn | 1361 | — |
Frequently asked questions
Is MiniMax-M2 better than o1-pro?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 31.5 on the Noometry Index.
Which is cheaper, MiniMax-M2 or o1-pro?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; o1-pro lists at $150 and $600.
Which has the bigger context window?
MiniMax-M2 does, with 205K tokens against 200K.
How many benchmarks do MiniMax-M2 and o1-pro share?
0 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and o1-pro has 3.