Model comparison
MiniMax-M2.1 vs o1-mini
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 34.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. MiniMax-M2.1 scores higher in 9 categories and o1-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 48.4.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.1 | o1-mini | |
|---|---|---|
| Provider | MiniMax | OpenAI |
| Noometry Index | 38.9 | 34.0 |
| Released | 2025-12-23 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 22 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
MiniMax-M2.1: 40.4 (#143), o1-mini: 35.5 (#224)
| Benchmark | MiniMax-M2.1 | o1-mini |
|---|---|---|
| LMArena Coding | 1421 | 1362 |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1384 | — |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| ALE-Bench | 623.83 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use MiniMax-M2.1 leads
MiniMax-M2.1: 27.9 (#98), o1-mini: 24.6 (#118)
| Benchmark | MiniMax-M2.1 | o1-mini |
|---|---|---|
| Terminal-Bench | 36.6% | — |
| Cybench | — | 10% |
Reasoning MiniMax-M2.1 leads
MiniMax-M2.1: 16.6 (#302), o1-mini: 8.8 (#346)
| Benchmark | MiniMax-M2.1 | o1-mini |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1333 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| NYT Connections (extended) | 11.2% | — |
| ARC-AGI-1 | — | 14% |
| LiveBench Reasoning | — | 72.3% |
| LiveBench Data Analysis | — | 57.9% |
| Epoch Capabilities Index | — | 135.82 |
| LiveBench | — | 57.8% |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#138), o1-mini: 35.4 (#186)
| Benchmark | MiniMax-M2.1 | o1-mini |
|---|---|---|
| LMArena Math | 1397 | 1358 |
| OTIS Mock AIME 2024-2025 | — | 46.9% |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#147), o1-mini: 34.9 (#192)
| Benchmark | MiniMax-M2.1 | o1-mini |
|---|---|---|
| LMArena Expert | 1431 | 1316 |
| GPQA Diamond | — | 62.4% |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 11.8% | — |
Multilingual MiniMax-M2.1 leads
MiniMax-M2.1: 50.0 (#128), o1-mini: 43.6 (#182)
| Benchmark | MiniMax-M2.1 | o1-mini |
|---|---|---|
| LMArena Non-English | 1378 | 1289 |
| LMArena Chinese | 1430 | 1314 |
| LMArena French | 1404 | 1293 |
| LMArena German | 1381 | 1278 |
| LMArena Japanese | 1287 | 1245 |
| LMArena Korean | 1298 | 1223 |
| LMArena Russian | 1387 | 1283 |
| LMArena Spanish | 1397 | 1303 |
Instruction Following MiniMax-M2.1 leads
MiniMax-M2.1: 73.8 (#112), o1-mini: 66.7 (#206)
| Benchmark | MiniMax-M2.1 | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1400 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context MiniMax-M2.1 leads
MiniMax-M2.1: 43.2 (#101), o1-mini: 40.1 (#161)
| Benchmark | MiniMax-M2.1 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1416 | 1320 |
Writing & Preference MiniMax-M2.1 leads
MiniMax-M2.1: 58.3 (#120), o1-mini: 48.4 (#202)
| Benchmark | MiniMax-M2.1 | o1-mini |
|---|---|---|
| LMArena Text | 1392 | 1317 |
| LMArena Creative Writing | 1361 | 1244 |
| LMArena Multi-Turn | 1396 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is MiniMax-M2.1 better than o1-mini?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 34.0 on the Noometry Index.
Is MiniMax-M2.1 or o1-mini better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 35.5 in the Noometry coding category.
How many benchmarks do MiniMax-M2.1 and o1-mini share?
17 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and o1-mini has 39.