# Mercury vs MiniMax-M2

> Mercury and MiniMax-M2 score almost the same on the Noometry Index (37.3 vs 36.9), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/mercury-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. Mercury scores higher in 0 categories and MiniMax-M2 in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2 leads 53.3 to 46.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 21.6% for Mercury and 57.8% for MiniMax-M2.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury | MiniMax-M2 |
|---|---|---|
| Provider | Inception | MiniMax |
| Noometry Index | 37.3 | 36.9 |
| Rank | 192 | 201 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Mercury: 38.1 (#164)
- MiniMax-M2: 39.1 (#151)

| Benchmark | Mercury | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1323 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |

## Agentic & Tool Use

- Mercury: —
- MiniMax-M2: 24.9 (#102)

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

## Reasoning

- Mercury: 16.8 (#288)
- MiniMax-M2: 18.6 (#256)

| Benchmark | Mercury | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 21.6% | 57.8% |
| LMArena Hard Prompts | 1284 | 1357 |
| NYT Connections (extended) | — | 14.8% |

## Math

- Mercury: —
- MiniMax-M2: 34.6 (#158)

| Benchmark | Mercury | MiniMax-M2 |
|---|---|---|
| LMArena Math | — | 1350 |

## Knowledge

- Mercury: —
- MiniMax-M2: 36.3 (#160)

| Benchmark | Mercury | MiniMax-M2 |
|---|---|---|
| LMArena Expert | — | 1336 |

## Multilingual

- Mercury: 41.7 (#201)
- MiniMax-M2: 45.6 (#165)

| Benchmark | Mercury | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1259 | 1314 |
| LMArena Chinese | — | 1367 |
| LMArena French | — | 1336 |
| LMArena German | — | 1366 |
| LMArena Russian | — | 1332 |
| LMArena Spanish | — | 1326 |

## Instruction Following

- Mercury: 65.3 (#220)
- MiniMax-M2: 70.4 (#160)

| Benchmark | Mercury | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1238 | 1329 |

## Long Context

- Mercury: 38.3 (#193)
- MiniMax-M2: 40.5 (#148)

| Benchmark | Mercury | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1264 | 1332 |

## Writing & Preference

- Mercury: 46.2 (#216)
- MiniMax-M2: 53.3 (#157)

| Benchmark | Mercury | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1282 | 1340 |
| LMArena Creative Writing | 1186 | 1288 |
| LMArena Multi-Turn | 1283 | 1362 |

## FAQ

### Is Mercury better than MiniMax-M2?

Mercury and MiniMax-M2 score almost the same on the Noometry Index (37.3 vs 36.9), so choose on price, context window or the category you care about most.

### Is Mercury or MiniMax-M2 better for coding?

They score almost the same on coding (38.1 vs 39.1); test both on your own repository before choosing.

### How many benchmarks do Mercury and MiniMax-M2 share?

9 benchmarks have published results for both models. Mercury has 9 scored results on Noometry and MiniMax-M2 has 21.