# ERNIE 5.1 vs MiniMax-M2

> ERNIE 5.1 is the stronger model overall, scoring 43.1 to 36.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and MiniMax-M2 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.3 to 53.3.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 14.8% for MiniMax-M2.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.1 | MiniMax-M2 |
|---|---|---|
| Provider | Baidu | MiniMax |
| Noometry Index | 43.1 | 36.9 |
| Rank | 87 | 201 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.1: 43.4 (#78)
- MiniMax-M2: 39.1 (#151)

| Benchmark | ERNIE 5.1 | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1488 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |

## Agentic & Tool Use

- ERNIE 5.1: —
- MiniMax-M2: 24.9 (#102)

| Benchmark | ERNIE 5.1 | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| LMArena Search | 1227 | — |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- ERNIE 5.1: 20.9 (#209)
- MiniMax-M2: 18.6 (#256)

| Benchmark | ERNIE 5.1 | MiniMax-M2 |
|---|---|---|
| NYT Connections (extended) | 23.4% | 14.8% |
| LMArena Hard Prompts | 1481 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |

## Math

- ERNIE 5.1: 37.5 (#96)
- MiniMax-M2: 34.6 (#158)

| Benchmark | ERNIE 5.1 | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1481 | 1350 |

## Knowledge

- ERNIE 5.1: 41.2 (#103)
- MiniMax-M2: 36.3 (#160)

| Benchmark | ERNIE 5.1 | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1491 | 1336 |

## Multilingual

- ERNIE 5.1: 55.7 (#28)
- MiniMax-M2: 45.6 (#165)

| Benchmark | ERNIE 5.1 | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1455 | 1314 |
| LMArena Chinese | 1507 | 1367 |
| LMArena French | 1486 | 1336 |
| LMArena German | 1470 | 1366 |
| LMArena Russian | 1459 | 1332 |
| LMArena Spanish | 1472 | 1326 |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1428 | — |

## Instruction Following

- ERNIE 5.1: 76.9 (#35)
- MiniMax-M2: 70.4 (#160)

| Benchmark | ERNIE 5.1 | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1329 |

## Long Context

- ERNIE 5.1: 44.7 (#56)
- MiniMax-M2: 40.5 (#148)

| Benchmark | ERNIE 5.1 | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1462 | 1332 |

## Writing & Preference

- ERNIE 5.1: 65.3 (#50)
- MiniMax-M2: 53.3 (#157)

| Benchmark | ERNIE 5.1 | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1468 | 1340 |
| LMArena Creative Writing | 1440 | 1288 |
| LMArena Multi-Turn | 1471 | 1362 |

## FAQ

### Is ERNIE 5.1 better than MiniMax-M2?

ERNIE 5.1 is the stronger model overall, scoring 43.1 to 36.9 on the Noometry Index.

### Is ERNIE 5.1 or MiniMax-M2 better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 39.1 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and MiniMax-M2 share?

16 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and MiniMax-M2 has 21.