# MiniMax-M2 vs Wizardlm 70b

> MiniMax-M2 is the stronger model overall, scoring 37.4 to 33.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-vs-wizardlm-70b
- Last updated: 2026-10-11
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. MiniMax-M2 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 leads 53.0 to 34.8.

## Snapshot

| | MiniMax-M2 | Wizardlm 70b |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 37.4 | 33.0 |
| Rank | 204 | 249 |
| Context | 205K | — |
| Input $/M | $0.30 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- MiniMax-M2: 39.3 (#159)
- Wizardlm 70b: 31.4 (#285)

| Benchmark | MiniMax-M2 | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1370 | 1081 |
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |

## Agentic & Tool Use

- MiniMax-M2: 25.1 (#109)
- Wizardlm 70b: —

| Benchmark | MiniMax-M2 | Wizardlm 70b |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |

## Reasoning

- MiniMax-M2: 19.4 (#258)
- Wizardlm 70b: 20.7 (#234)

| Benchmark | MiniMax-M2 | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1357 | 1079 |
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |

## Math

- MiniMax-M2: 37.3 (#160)
- Wizardlm 70b: 32.2 (#218)

| Benchmark | MiniMax-M2 | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1352 | 1116 |

## Knowledge

- MiniMax-M2: 37.0 (#163)
- Wizardlm 70b: —

| Benchmark | MiniMax-M2 | Wizardlm 70b |
|---|---|---|
| LMArena Expert | 1337 | — |

## Multilingual

- MiniMax-M2: 45.3 (#171)
- Wizardlm 70b: 29.6 (#265)

| Benchmark | MiniMax-M2 | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1313 | 1078 |
| LMArena Chinese | 1366 | 1052 |
| LMArena German | 1355 | 1083 |
| LMArena Russian | 1331 | 1155 |
| LMArena French | 1335 | — |
| LMArena Spanish | 1326 | — |

## Instruction Following

- MiniMax-M2: 70.2 (#166)
- Wizardlm 70b: 56.3 (#273)

| Benchmark | MiniMax-M2 | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1328 | 1093 |

## Long Context

- MiniMax-M2: 40.5 (#153)
- Wizardlm 70b: 33.3 (#263)

| Benchmark | MiniMax-M2 | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1331 | 1097 |

## Writing & Preference

- MiniMax-M2: 53.0 (#162)
- Wizardlm 70b: 34.8 (#269)

| Benchmark | MiniMax-M2 | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1340 | 1120 |
| LMArena Creative Writing | 1286 | 1149 |
| LMArena Multi-Turn | 1361 | 1108 |

## FAQ

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

MiniMax-M2 is the stronger model overall, scoring 37.4 to 33.0 on the Noometry Index.

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

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 31.4 in the Noometry coding category.

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

12 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Wizardlm 70b has 12.