# Grok 4.6 vs MiniMax-M3

> Grok 4.6 is the stronger model overall, scoring 56.8 to 43.5 on the Noometry Index. MiniMax-M3 costs 5.7× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/grok-4-6-vs-minimax-m3
- Last updated: 2026-10-10
- Shared benchmarks: 36

## Summary

- They share 36 benchmarks with published results for both. Grok 4.6 scores higher in 9 categories and MiniMax-M3 in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.3 to 29.3.
- The biggest single-benchmark swing is FrontierCode: 48% for Grok 4.6 and 14.7% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $6 for Grok 4.6.
- MiniMax-M3 accepts more context: 1M tokens versus 500K.
- MiniMax-M3 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 56.8 | 43.5 |
| Rank | 19 | 81 |
| Context | 500K | 1M |
| Input $/M | $2 | $0.30 |
| Output $/M | $6 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Grok 4.6: 58.0 (#14)
- MiniMax-M3: 41.5 (#111)

| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| FrontierCode | 48% | 14.7% |
| LMArena WebDev | 1620 | 1482 |
| SciCode | 56.5% | 47.1% |
| LMArena Coding | 1464 | 1470 |
| ALE-Bench | 1,508 | 640.02 |
| DeepSWE | 67.5% | — |
| CursorBench | 41.4% | — |
| FrontierSWE | 25.3% | — |
| WeirdML | 67.3% | — |

## Agentic & Tool Use

- Grok 4.6: 39.4 (#25)
- MiniMax-M3: 22.5 (#121)

| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| APEX-Agents | 65.3% | 37.7% |
| Vending-Bench 2 | 9,047 | 2,158 |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| GDP.pdf | 17.2% | — |

## Reasoning

- Grok 4.6: 61.3 (#18)
- MiniMax-M3: 29.3 (#83)

| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| SimpleBench | 75.9% | 45.8% |
| NYT Connections (extended) | 80% | 65.1% |
| CritPt | 19.7% | 3.7% |
| Chess Puzzles | 40% | 14% |
| LMArena Hard Prompts | 1445 | 1447 |
| Mystery Game Puzzles | 34% | 8% |
| DTBench | 97.3% | 78.9% |
| LMCA | 48.5% | 33.7% |
| Epoch Capabilities Index | 156.48 | 147 |
| ARC-AGI-2 | 67.1% | — |
| ARC-AGI-1 | 87.5% | — |
| EBR-Bench | 30.5% | — |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |

## Math

- Grok 4.6: 66.8 (#19)
- MiniMax-M3: 39.1 (#83)

| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.2% | 71.1% |
| ProofBench | 51% | 18% |
| LMArena Math | 1416 | 1432 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |

## Knowledge

- Grok 4.6: 63.3 (#18)
- MiniMax-M3: 58.4 (#32)

| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 94% | 90.9% |
| LMArena Expert | 1463 | 1462 |
| SimpleQA Verified | 49.3% | — |

## Multimodal

- Grok 4.6: 43.9 (#18)
- MiniMax-M3: 39.5 (#45)

| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1265 | 1254 |
| LMArena Document | 1452 | 1435 |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |

## Multilingual

- Grok 4.6: 53.3 (#67)
- MiniMax-M3: 53.2 (#70)

| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1422 | 1420 |
| LMArena Chinese | 1479 | 1465 |
| LMArena French | 1458 | 1445 |
| LMArena German | 1425 | 1424 |
| LMArena Japanese | 1383 | 1381 |
| LMArena Korean | 1395 | 1372 |
| LMArena Russian | 1427 | 1430 |
| LMArena Spanish | 1408 | 1431 |

## Instruction Following

- Grok 4.6: 75.6 (#59)
- MiniMax-M3: 75.7 (#56)

| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1431 | 1433 |

## Long Context

- Grok 4.6: 44.4 (#62)
- MiniMax-M3: 44.2 (#68)

| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1453 | 1445 |

## Writing & Preference

- Grok 4.6: 62.5 (#77)
- MiniMax-M3: 62.3 (#79)

| Benchmark | Grok 4.6 | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1427 | 1433 |
| LMArena Creative Writing | 1430 | 1405 |
| LMArena Multi-Turn | 1422 | 1441 |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is Grok 4.6 better than MiniMax-M3?

Grok 4.6 is the stronger model overall, scoring 56.8 to 43.5 on the Noometry Index. MiniMax-M3 costs 5.7× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.

### Which is cheaper, Grok 4.6 or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Grok 4.6 lists at $2 and $6.

### Is Grok 4.6 or MiniMax-M3 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.0 versus 41.5 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 500K.

### How many benchmarks do Grok 4.6 and MiniMax-M3 share?

36 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and MiniMax-M3 has 41.