# Grok-2 (Dec 2024) vs MiniMax-M3

> MiniMax-M3 is the stronger model overall, scoring 43.8 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-2-vs-minimax-m3
- Last updated: 2026-10-11
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and MiniMax-M3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 29.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 71.1% for MiniMax-M3.
- MiniMax-M3 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-2 (Dec 2024) | MiniMax-M3 |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 33.7 | 43.8 |
| Rank | 239 | 85 |
| Context | — | 1M |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Grok-2 (Dec 2024): 33.3 (#258)
- MiniMax-M3: 41.8 (#118)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1287 | 1469 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| WeirdML | 22.2% | — |
| LiveBench Coding | 46.4% | — |
| ALE-Bench | — | 640.02 |

## Agentic & Tool Use

- Grok-2 (Dec 2024): —
- MiniMax-M3: 22.6 (#130)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- Grok-2 (Dec 2024): 16.9 (#299)
- MiniMax-M3: 30.1 (#87)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M3 |
|---|---|---|
| SimpleBench | 22.7% | 45.8% |
| LMArena Hard Prompts | 1272 | 1447 |
| DTBench | 65.2% | 78.9% |
| Epoch Capabilities Index | 130.48 | 146.95 |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| LiveBench Reasoning | 54.8% | — |
| Mystery Game Puzzles | — | 8% |
| LiveBench Data Analysis | 54.5% | — |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |
| LiveBench | 54.3% | — |

## Math

- Grok-2 (Dec 2024): 20.8 (#284)
- MiniMax-M3: 40.0 (#95)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 71.1% |
| LMArena Math | 1283 | 1429 |
| ProofBench | — | 18% |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |

## Knowledge

- Grok-2 (Dec 2024): 29.8 (#233)
- MiniMax-M3: 58.4 (#35)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 53.8% | 90.9% |
| LMArena Expert | 1254 | 1461 |
| Confabulations | 20.1% | — |

## Multimodal

- Grok-2 (Dec 2024): —
- MiniMax-M3: 40.2 (#51)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |

## Multilingual

- Grok-2 (Dec 2024): 43.1 (#188)
- MiniMax-M3: 53.0 (#75)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1282 | 1420 |
| LMArena Chinese | 1289 | 1463 |
| LMArena French | 1318 | 1447 |
| LMArena German | 1287 | 1426 |
| LMArena Japanese | 1244 | 1381 |
| LMArena Korean | 1237 | 1372 |
| LMArena Russian | 1286 | 1428 |
| LMArena Spanish | 1281 | 1432 |

## Instruction Following

- Grok-2 (Dec 2024): 66.9 (#202)
- MiniMax-M3: 75.5 (#62)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1270 | 1433 |
| LiveBench Instruction Following | 69.6% | — |

## Long Context

- Grok-2 (Dec 2024): 38.8 (#190)
- MiniMax-M3: 44.2 (#72)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1276 | 1445 |

## Writing & Preference

- Grok-2 (Dec 2024): 48.6 (#198)
- MiniMax-M3: 62.1 (#83)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1305 | 1433 |
| LMArena Creative Writing | 1284 | 1404 |
| LMArena Multi-Turn | 1290 | 1442 |
| Short-Story Creative Writing | 63.6% | — |
| EQ-Bench 4 | — | 1150 |
| LiveBench Language | 45.6% | — |

## FAQ

### Is Grok-2 (Dec 2024) better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 33.7 on the Noometry Index.

### Is Grok-2 (Dec 2024) or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 33.3 in the Noometry coding category.

### How many benchmarks do Grok-2 (Dec 2024) and MiniMax-M3 share?

22 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and MiniMax-M3 has 41.