# Grok-2 (Dec 2024) vs MiniMax-M2.7

> MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-2-vs-minimax-m2-7
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and MiniMax-M2.7 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.7 leads 58.9 to 48.6.
- The biggest single-benchmark swing is WeirdML: 22.2% for Grok-2 (Dec 2024) and 37% for MiniMax-M2.7.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-2 (Dec 2024) | MiniMax-M2.7 |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 33.7 | 37.7 |
| Rank | 239 | 196 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Grok-2 (Dec 2024): 33.3 (#258)
- MiniMax-M2.7: 41.8 (#120)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.7 |
|---|---|---|
| WeirdML | 22.2% | 37% |
| LMArena Coding | 1287 | 1454 |
| LMArena WebDev | — | 1398 |
| SciCode | — | 47% |
| LiveBench Coding | 46.4% | — |
| ALE-Bench | — | 599.25 |

## Agentic & Tool Use

- Grok-2 (Dec 2024): —
- MiniMax-M2.7: 25.1 (#111)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |

## Reasoning

- Grok-2 (Dec 2024): 16.9 (#299)
- MiniMax-M2.7: 19.7 (#253)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1422 |
| Epoch Capabilities Index | 130.48 | 145.85 |
| SimpleBench | 22.7% | — |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| LiveBench Reasoning | 54.8% | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| LiveBench | 54.3% | — |

## Math

- Grok-2 (Dec 2024): 20.8 (#284)
- MiniMax-M2.7: 25.9 (#263)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1283 | 1420 |
| OTIS Mock AIME 2024-2025 | 11.5% | — |
| ProofBench | — | 3% |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |

## Knowledge

- Grok-2 (Dec 2024): 29.8 (#233)
- MiniMax-M2.7: 37.7 (#152)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1254 | 1444 |
| GPQA Diamond | 53.8% | — |
| Confabulations | 20.1% | — |
| Vectara Hallucination Rate | — | 12.9% |

## Multilingual

- Grok-2 (Dec 2024): 43.1 (#188)
- MiniMax-M2.7: 50.3 (#123)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1282 | 1382 |
| LMArena Chinese | 1289 | 1441 |
| LMArena French | 1318 | 1421 |
| LMArena German | 1287 | 1398 |
| LMArena Japanese | 1244 | 1262 |
| LMArena Korean | 1237 | 1313 |
| LMArena Russian | 1286 | 1383 |
| LMArena Spanish | 1281 | 1403 |

## Instruction Following

- Grok-2 (Dec 2024): 66.9 (#202)
- MiniMax-M2.7: 74.1 (#103)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1270 | 1405 |
| LiveBench Instruction Following | 69.6% | — |

## Long Context

- Grok-2 (Dec 2024): 38.8 (#190)
- MiniMax-M2.7: 43.3 (#99)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1276 | 1419 |

## Writing & Preference

- Grok-2 (Dec 2024): 48.6 (#198)
- MiniMax-M2.7: 58.9 (#112)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1305 | 1405 |
| LMArena Creative Writing | 1284 | 1354 |
| LMArena Multi-Turn | 1290 | 1412 |
| Short-Story Creative Writing | 63.6% | — |
| LiveBench Language | 45.6% | — |

## FAQ

### Is Grok-2 (Dec 2024) better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 33.7 on the Noometry Index.

### Is Grok-2 (Dec 2024) or MiniMax-M2.7 better for coding?

MiniMax-M2.7 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-M2.7 share?

19 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and MiniMax-M2.7 has 30.