Model comparison
MiniMax-M2.1 vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 38.9 on the Noometry Index. MiniMax-M2.1 costs 3.7× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
MiniMaxSummary
- They share 19 benchmarks with published results for both. MiniMax-M2.1 scores higher in 2 categories and o4-mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where o4-mini leads 24.6 to 16.6.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 11.8% for MiniMax-M2.1 and 18.6% for o4-mini.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- MiniMax-M2.1 accepts more context: 205K tokens versus 200K.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.1 | o4-mini | |
|---|---|---|
| Provider | MiniMax | OpenAI |
| Noometry Index | 38.9 | 41.6 |
| Released | 2025-12-23 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 205K | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $0.30 | $1.10 |
| Output $ / M tokens | $1.20 | $4.40 |
| Results tracked | 22 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
MiniMax-M2.1: 40.4 (#143), o4-mini: 40.9 (#127)
| Benchmark | MiniMax-M2.1 | o4-mini |
|---|---|---|
| LMArena Coding | 1421 | 1368 |
| ALE-Bench | 623.83 | 826.17 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1384 | — |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use o4-mini leads
MiniMax-M2.1: 27.9 (#98), o4-mini: 32.6 (#61)
| Benchmark | MiniMax-M2.1 | o4-mini |
|---|---|---|
| Terminal-Bench | 36.6% | — |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
MiniMax-M2.1: 16.6 (#302), o4-mini: 24.6 (#162)
| Benchmark | MiniMax-M2.1 | o4-mini |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1351 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 11.2% | — |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LMCA | — | 26.5% |
| Epoch Capabilities Index | — | 145.64 |
| ForecastBench | — | 61.8 |
Math o4-mini leads
MiniMax-M2.1: 38.3 (#138), o4-mini: 40.8 (#89)
| Benchmark | MiniMax-M2.1 | o4-mini |
|---|---|---|
| LMArena Math | 1397 | 1389 |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
MiniMax-M2.1: 38.3 (#147), o4-mini: 43.6 (#91)
| Benchmark | MiniMax-M2.1 | o4-mini |
|---|---|---|
| Vectara Hallucination Rate | 11.8% | 18.6% |
| LMArena Expert | 1431 | 1343 |
| GPQA Diamond | — | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
Multimodal Not comparable
MiniMax-M2.1: —, o4-mini: 40.2 (#49)
| Benchmark | MiniMax-M2.1 | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual MiniMax-M2.1 leads
MiniMax-M2.1: 50.0 (#128), o4-mini: 47.0 (#154)
| Benchmark | MiniMax-M2.1 | o4-mini |
|---|---|---|
| LMArena Non-English | 1378 | 1337 |
| LMArena Chinese | 1430 | 1354 |
| LMArena French | 1404 | 1364 |
| LMArena German | 1381 | 1336 |
| LMArena Japanese | 1287 | 1308 |
| LMArena Korean | 1298 | 1312 |
| LMArena Russian | 1387 | 1334 |
| LMArena Spanish | 1397 | 1347 |
Instruction Following o4-mini leads
MiniMax-M2.1: 73.8 (#112), o4-mini: 75.2 (#68)
| Benchmark | MiniMax-M2.1 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1400 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
MiniMax-M2.1: 43.2 (#101), o4-mini: 45.5 (#33)
| Benchmark | MiniMax-M2.1 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1416 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference MiniMax-M2.1 leads
MiniMax-M2.1: 58.3 (#120), o4-mini: 54.0 (#152)
| Benchmark | MiniMax-M2.1 | o4-mini |
|---|---|---|
| LMArena Text | 1392 | 1353 |
| LMArena Creative Writing | 1361 | 1294 |
| LMArena Multi-Turn | 1396 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
Frequently asked questions
Is MiniMax-M2.1 better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 38.9 on the Noometry Index. MiniMax-M2.1 costs 3.7× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2.1 or o4-mini?
MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is MiniMax-M2.1 or o4-mini better for coding?
They score almost the same on coding (40.4 vs 40.9); test both on your own repository before choosing.
Which has the bigger context window?
MiniMax-M2.1 does, with 205K tokens against 200K.
How many benchmarks do MiniMax-M2.1 and o4-mini share?
19 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and o4-mini has 60.