Model comparison
Grok 4.1 vs MiniMax-M2
Grok 4.1 is the stronger model overall, scoring 40.8 to 36.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
MiniMaxSummary
- They share 16 benchmarks with published results for both. Grok 4.1 scores higher in 8 categories and MiniMax-M2 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.1 leads 28.3 to 18.6.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.1 | MiniMax-M2 | |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 40.8 | 36.9 |
| Released | 2025-11-17 | 2025-10-27 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 19 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Grok 4.1: 33.4 (#246), MiniMax-M2: 39.1 (#151)
| Benchmark | Grok 4.1 | MiniMax-M2 |
|---|---|---|
| LMArena WebDev | 1214 | 1297 |
| LMArena Coding | 1445 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
Agentic & Tool Use Grok 4.1 leads
Grok 4.1: 33.8 (#47), MiniMax-M2: 24.9 (#102)
| Benchmark | Grok 4.1 | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Cybench | 39% | — |
| Vending-Bench 2 | — | 160.6 |
Reasoning Grok 4.1 leads
Grok 4.1: 28.3 (#91), MiniMax-M2: 18.6 (#256)
| Benchmark | Grok 4.1 | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1436 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
Math Grok 4.1 leads
Grok 4.1: 36.2 (#124), MiniMax-M2: 34.6 (#158)
| Benchmark | Grok 4.1 | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1422 | 1350 |
Knowledge Grok 4.1 leads
Grok 4.1: 38.9 (#129), MiniMax-M2: 36.3 (#160)
| Benchmark | Grok 4.1 | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1417 | 1336 |
Multilingual Grok 4.1 leads
Grok 4.1: 53.6 (#64), MiniMax-M2: 45.6 (#165)
| Benchmark | Grok 4.1 | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1425 | 1314 |
| LMArena Chinese | 1464 | 1367 |
| LMArena French | 1448 | 1336 |
| LMArena German | 1447 | 1366 |
| LMArena Russian | 1434 | 1332 |
| LMArena Spanish | 1438 | 1326 |
| LMArena Japanese | 1396 | — |
| LMArena Korean | 1407 | — |
Instruction Following Grok 4.1 leads
Grok 4.1: 74.0 (#106), MiniMax-M2: 70.4 (#160)
| Benchmark | Grok 4.1 | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1400 | 1329 |
Long Context Grok 4.1 leads
Grok 4.1: 43.2 (#96), MiniMax-M2: 40.5 (#148)
| Benchmark | Grok 4.1 | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1416 | 1332 |
Writing & Preference Grok 4.1 leads
Grok 4.1: 62.6 (#71), MiniMax-M2: 53.3 (#157)
| Benchmark | Grok 4.1 | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1437 | 1340 |
| LMArena Creative Writing | 1411 | 1288 |
| LMArena Multi-Turn | 1438 | 1362 |
Frequently asked questions
Is Grok 4.1 better than MiniMax-M2?
Grok 4.1 is the stronger model overall, scoring 40.8 to 36.9 on the Noometry Index.
Is Grok 4.1 or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.1 versus 33.4 in the Noometry coding category.
How many benchmarks do Grok 4.1 and MiniMax-M2 share?
16 benchmarks have published results for both models. Grok 4.1 has 19 scored results on Noometry and MiniMax-M2 has 21.