# MiniMax-M2.1 vs Wizardlm 70b

> MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-1-vs-wizardlm-70b
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. MiniMax-M2.1 scores higher in 6 categories and Wizardlm 70b in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.5 to 34.9.

## Snapshot

| | MiniMax-M2.1 | Wizardlm 70b |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 38.4 | 32.4 |
| Rank | 177 | 245 |
| Context | 205K | — |
| Input $/M | $0.30 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- MiniMax-M2.1: 40.1 (#132)
- Wizardlm 70b: 30.9 (#280)

| Benchmark | MiniMax-M2.1 | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1421 | 1081 |
| LMArena WebDev | 1384 | — |
| ALE-Bench | 623.83 | — |

## Agentic & Tool Use

- MiniMax-M2.1: 27.7 (#91)
- Wizardlm 70b: —

| Benchmark | MiniMax-M2.1 | Wizardlm 70b |
|---|---|---|
| Terminal-Bench | 36.6% | — |

## Reasoning

- MiniMax-M2.1: 15.8 (#301)
- Wizardlm 70b: 19.8 (#231)

| Benchmark | MiniMax-M2.1 | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1410 | 1079 |
| NYT Connections (extended) | 11.2% | — |

## Math

- MiniMax-M2.1: 35.6 (#142)
- Wizardlm 70b: 29.7 (#216)

| Benchmark | MiniMax-M2.1 | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1396 | 1116 |

## Knowledge

- MiniMax-M2.1: 37.7 (#143)
- Wizardlm 70b: —

| Benchmark | MiniMax-M2.1 | Wizardlm 70b |
|---|---|---|
| Vectara Hallucination Rate | 11.8% | — |
| LMArena Expert | 1432 | — |

## Multilingual

- MiniMax-M2.1: 50.2 (#123)
- Wizardlm 70b: 29.8 (#260)

| Benchmark | MiniMax-M2.1 | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1378 | 1078 |
| LMArena Chinese | 1430 | 1052 |
| LMArena German | 1380 | 1083 |
| LMArena Russian | 1386 | 1155 |
| LMArena French | 1405 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1297 | — |
| LMArena Spanish | 1396 | — |

## Instruction Following

- MiniMax-M2.1: 74.0 (#108)
- Wizardlm 70b: 56.5 (#268)

| Benchmark | MiniMax-M2.1 | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1399 | 1093 |

## Long Context

- MiniMax-M2.1: 43.2 (#98)
- Wizardlm 70b: 33.3 (#258)

| Benchmark | MiniMax-M2.1 | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1416 | 1097 |

## Writing & Preference

- MiniMax-M2.1: 58.5 (#114)
- Wizardlm 70b: 34.9 (#264)

| Benchmark | MiniMax-M2.1 | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1392 | 1120 |
| LMArena Creative Writing | 1362 | 1149 |
| LMArena Multi-Turn | 1396 | 1108 |

## FAQ

### Is MiniMax-M2.1 better than Wizardlm 70b?

MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 32.4 on the Noometry Index.

### Is MiniMax-M2.1 or Wizardlm 70b better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.1 versus 30.9 in the Noometry coding category.

### How many benchmarks do MiniMax-M2.1 and Wizardlm 70b share?

12 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Wizardlm 70b has 12.