Model comparison
Grok-3 mini vs MiniMax-M2.1
Grok-3 mini is the stronger model overall, scoring 41.2 to 38.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMaxSummary
- They share 17 benchmarks with published results for both. Grok-3 mini scores higher in 4 categories and MiniMax-M2.1 in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 38.3.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | MiniMax-M2.1 | |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 41.2 | 38.9 |
| Released | 2025-04-09 | 2025-12-23 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 35 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok-3 mini: 40.8 (#131), MiniMax-M2.1: 40.4 (#143)
| Benchmark | Grok-3 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1379 | 1421 |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1384 |
| WeirdML | 42.6% | — |
| ALE-Bench | — | 623.83 |
Agentic & Tool Use Not comparable
Grok-3 mini: —, MiniMax-M2.1: 27.9 (#98)
| Benchmark | Grok-3 mini | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning MiniMax-M2.1 leads
Grok-3 mini: 13.6 (#334), MiniMax-M2.1: 16.6 (#302)
| Benchmark | Grok-3 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1411 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 11.2% |
| ARC-AGI-1 | 16.5% | — |
| Epoch Capabilities Index | 140.35 | — |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), MiniMax-M2.1: 38.3 (#138)
| Benchmark | Grok-3 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1386 | 1397 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.4 (#81), MiniMax-M2.1: 38.3 (#147)
| Benchmark | Grok-3 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1395 | 1431 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| Vectara Hallucination Rate | — | 11.8% |
| GPQA (HELM) | 67.5% | — |
Multilingual MiniMax-M2.1 leads
Grok-3 mini: 48.1 (#145), MiniMax-M2.1: 50.0 (#128)
| Benchmark | Grok-3 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1352 | 1378 |
| LMArena Chinese | 1387 | 1430 |
| LMArena French | 1357 | 1404 |
| LMArena German | 1349 | 1381 |
| LMArena Japanese | 1342 | 1287 |
| LMArena Korean | 1335 | 1298 |
| LMArena Russian | 1353 | 1387 |
| LMArena Spanish | 1381 | 1397 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), MiniMax-M2.1: 73.8 (#112)
| Benchmark | Grok-3 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1400 |
| IFEval | 95.1% | — |
Long Context MiniMax-M2.1 leads
Grok-3 mini: 41.0 (#147), MiniMax-M2.1: 43.2 (#101)
| Benchmark | Grok-3 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1372 | 1416 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference MiniMax-M2.1 leads
Grok-3 mini: 52.5 (#169), MiniMax-M2.1: 58.3 (#120)
| Benchmark | Grok-3 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1370 | 1392 |
| LMArena Creative Writing | 1342 | 1361 |
| LMArena Multi-Turn | 1355 | 1396 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than MiniMax-M2.1?
Grok-3 mini is the stronger model overall, scoring 41.2 to 38.9 on the Noometry Index.
Is Grok-3 mini or MiniMax-M2.1 better for coding?
They score almost the same on coding (40.8 vs 40.4); test both on your own repository before choosing.
How many benchmarks do Grok-3 mini and MiniMax-M2.1 share?
17 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and MiniMax-M2.1 has 22.