# Mercury 2.5 vs MiniMax-M3

> MiniMax-M3 has enough public results to be ranked (#81); Mercury 2.5 does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/mercury-2-5-vs-minimax-m3
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Mercury 2.5 scores higher in 0 categories and MiniMax-M3 in 1 category; one gap is clear of the uncertainty.
- The widest gap is in math, where MiniMax-M3 leads 39.1 to 22.4.
- The biggest single-benchmark swing is ProofBench: 3% for Mercury 2.5 and 18% for MiniMax-M3.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 260K.
- MiniMax-M3 has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2.5 | MiniMax-M3 |
|---|---|---|
| Provider | Inception | MiniMax |
| Noometry Index | 30.2 | 43.5 |
| Rank | — | 81 |
| Context | 260K | 1M |
| Input $/M | $0.04 | $0.30 |
| Output $/M | $0.15 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Mercury 2.5: —
- MiniMax-M3: 41.5 (#111)

| Benchmark | Mercury 2.5 | MiniMax-M3 |
|---|---|---|
| ALE-Bench | 301.65 | 640.02 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| LMArena Coding | — | 1470 |

## Agentic & Tool Use

- Mercury 2.5: —
- MiniMax-M3: 22.5 (#121)

| Benchmark | Mercury 2.5 | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- Mercury 2.5: —
- MiniMax-M3: 29.3 (#83)

| Benchmark | Mercury 2.5 | MiniMax-M3 |
|---|---|---|
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| LMArena Hard Prompts | — | 1447 |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 147 |
| ForecastBench | — | 61.4 |

## Math

- Mercury 2.5: 22.4
- MiniMax-M3: 39.1 (#83)

| Benchmark | Mercury 2.5 | MiniMax-M3 |
|---|---|---|
| ProofBench | 3% | 18% |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| LMArena Math | — | 1432 |

## Knowledge

- Mercury 2.5: —
- MiniMax-M3: 58.4 (#32)

| Benchmark | Mercury 2.5 | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | — | 90.9% |
| LMArena Expert | — | 1462 |

## Multimodal

- Mercury 2.5: —
- MiniMax-M3: 39.5 (#45)

| Benchmark | Mercury 2.5 | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1254 |
| LMArena Document | — | 1435 |

## Multilingual

- Mercury 2.5: —
- MiniMax-M3: 53.2 (#70)

| Benchmark | Mercury 2.5 | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | — | 1420 |
| LMArena Chinese | — | 1465 |
| LMArena French | — | 1445 |
| LMArena German | — | 1424 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Russian | — | 1430 |
| LMArena Spanish | — | 1431 |

## Instruction Following

- Mercury 2.5: —
- MiniMax-M3: 75.7 (#56)

| Benchmark | Mercury 2.5 | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | — | 1433 |

## Long Context

- Mercury 2.5: —
- MiniMax-M3: 44.2 (#68)

| Benchmark | Mercury 2.5 | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | — | 1445 |

## Writing & Preference

- Mercury 2.5: —
- MiniMax-M3: 62.3 (#79)

| Benchmark | Mercury 2.5 | MiniMax-M3 |
|---|---|---|
| LMArena Text | — | 1433 |
| LMArena Creative Writing | — | 1405 |
| EQ-Bench 4 | — | 1150 |
| LMArena Multi-Turn | — | 1441 |

## FAQ

### Is Mercury 2.5 better than MiniMax-M3?

MiniMax-M3 has enough public results to be ranked (#81); Mercury 2.5 does not yet, so treat this comparison as directional.

### Which is cheaper, Mercury 2.5 or MiniMax-M3?

Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.

### Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 260K.

### How many benchmarks do Mercury 2.5 and MiniMax-M3 share?

2 benchmarks have published results for both models. Mercury 2.5 has 2 scored results on Noometry and MiniMax-M3 has 41.