# MiniMax-M2 vs Solar Pro4

> Solar Pro4 is the stronger model overall, scoring 42.1 to 37.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-vs-solar-pro4
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. MiniMax-M2 scores higher in 0 categories and Solar Pro4 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Solar Pro4 leads 28.5 to 19.4.
- Both cost about the same: $0.30 input and $1.20 output per million tokens.
- Solar Pro4 accepts more context: 524K tokens versus 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | MiniMax-M2 | Solar Pro4 |
|---|---|---|
| Provider | MiniMax | Upstage |
| Noometry Index | 37.4 | 42.1 |
| Rank | 204 | 121 |
| Context | 205K | 524K |
| Input $/M | $0.30 | $0.30 |
| Output $/M | $1.20 | $1.20 |
| Weights | Open | Proprietary |

## Coding

- MiniMax-M2: 39.3 (#159)
- Solar Pro4: 40.1 (#149)

| Benchmark | MiniMax-M2 | Solar Pro4 |
|---|---|---|
| LMArena WebDev | 1297 | 1371 |
| LMArena Coding | 1370 | 1437 |
| SWE-bench Verified (bash only) | 61% | — |

## Agentic & Tool Use

- MiniMax-M2: 25.1 (#109)
- Solar Pro4: —

| Benchmark | MiniMax-M2 | Solar Pro4 |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |

## Reasoning

- MiniMax-M2: 19.4 (#258)
- Solar Pro4: 28.5 (#104)

| Benchmark | MiniMax-M2 | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1357 | 1399 |
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |

## Math

- MiniMax-M2: 37.3 (#160)
- Solar Pro4: 38.8 (#128)

| Benchmark | MiniMax-M2 | Solar Pro4 |
|---|---|---|
| LMArena Math | 1352 | 1416 |

## Knowledge

- MiniMax-M2: 37.0 (#163)
- Solar Pro4: 39.8 (#129)

| Benchmark | MiniMax-M2 | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1337 | 1427 |

## Multilingual

- MiniMax-M2: 45.3 (#171)
- Solar Pro4: 48.7 (#139)

| Benchmark | MiniMax-M2 | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1313 | 1361 |
| LMArena Chinese | 1366 | 1415 |
| LMArena French | 1335 | 1397 |
| LMArena German | 1355 | 1364 |
| LMArena Russian | 1331 | 1360 |
| LMArena Spanish | 1326 | 1401 |
| LMArena Japanese | — | 1309 |
| LMArena Korean | — | 1382 |

## Instruction Following

- MiniMax-M2: 70.2 (#166)
- Solar Pro4: 72.7 (#132)

| Benchmark | MiniMax-M2 | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1328 | 1377 |

## Long Context

- MiniMax-M2: 40.5 (#153)
- Solar Pro4: 42.1 (#130)

| Benchmark | MiniMax-M2 | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1331 | 1381 |

## Writing & Preference

- MiniMax-M2: 53.0 (#162)
- Solar Pro4: 56.5 (#138)

| Benchmark | MiniMax-M2 | Solar Pro4 |
|---|---|---|
| LMArena Text | 1340 | 1386 |
| LMArena Creative Writing | 1286 | 1316 |
| LMArena Multi-Turn | 1361 | 1385 |

## FAQ

### Is MiniMax-M2 better than Solar Pro4?

Solar Pro4 is the stronger model overall, scoring 42.1 to 37.4 on the Noometry Index.

### Which is cheaper, MiniMax-M2 or Solar Pro4?

Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.

### Is MiniMax-M2 or Solar Pro4 better for coding?

They score almost the same on coding (39.3 vs 40.1); test both on your own repository before choosing.

### Which has the bigger context window?

Solar Pro4 does, with 524K tokens against 205K.

### How many benchmarks do MiniMax-M2 and Solar Pro4 share?

16 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Solar Pro4 has 18.