# Grok-2 (Dec 2024) vs MiniMax-M2.5

> MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-2-vs-minimax-m2-5
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 1 category and MiniMax-M2.5 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 47.9 to 32.9.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-2 (Dec 2024) | MiniMax-M2.5 |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 33.4 | 38.1 |
| Rank | 233 | 181 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Grok-2 (Dec 2024): 32.9 (#254)
- MiniMax-M2.5: 47.9 (#53)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1288 | 1380 |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1386 |
| SWE-bench Multilingual | — | 68.3% |
| WeirdML | 22.2% | — |
| LiveBench Coding | 46.4% | — |
| ALE-Bench | — | 618.17 |

## Agentic & Tool Use

- Grok-2 (Dec 2024): —
- MiniMax-M2.5: 30.2 (#70)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |

## Reasoning

- Grok-2 (Dec 2024): 16.4 (#294)
- MiniMax-M2.5: 17.6 (#281)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1372 |
| Epoch Capabilities Index | 130.48 | 146.68 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | 22.7% | — |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| LiveBench Reasoning | 54.8% | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| LiveBench | 54.3% | — |

## Math

- Grok-2 (Dec 2024): 19.6 (#278)
- MiniMax-M2.5: 25.8 (#242)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1283 | 1378 |
| OTIS Mock AIME 2024-2025 | 11.5% | — |
| ProofBench | — | 4% |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |

## Knowledge

- Grok-2 (Dec 2024): 29.8 (#225)
- MiniMax-M2.5: 38.6 (#132)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1254 | 1378 |
| GPQA Diamond | 53.8% | — |
| Confabulations | 20.1% | — |
| Vectara Hallucination Rate | — | 9.1% |

## Multilingual

- Grok-2 (Dec 2024): 43.3 (#183)
- MiniMax-M2.5: 47.3 (#147)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1282 | 1338 |
| LMArena Chinese | 1289 | 1392 |
| LMArena French | 1317 | 1363 |
| LMArena German | 1287 | 1361 |
| LMArena Japanese | 1244 | 1169 |
| LMArena Korean | 1237 | 1232 |
| LMArena Russian | 1286 | 1359 |
| LMArena Spanish | 1281 | 1354 |

## Instruction Following

- Grok-2 (Dec 2024): 67.1 (#197)
- MiniMax-M2.5: 71.7 (#143)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1270 | 1353 |
| LiveBench Instruction Following | 69.6% | — |

## Long Context

- Grok-2 (Dec 2024): 38.7 (#186)
- MiniMax-M2.5: 37.4 (#211)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1276 | 1367 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |

## Writing & Preference

- Grok-2 (Dec 2024): 48.8 (#192)
- MiniMax-M2.5: 54.1 (#149)

| Benchmark | Grok-2 (Dec 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1305 | 1359 |
| LMArena Creative Writing | 1284 | 1331 |
| LMArena Multi-Turn | 1290 | 1364 |
| Short-Story Creative Writing | 63.6% | — |
| EQ-Bench Creative Writing | — | 1361 |
| LiveBench Language | 45.6% | — |

## FAQ

### Is Grok-2 (Dec 2024) better than MiniMax-M2.5?

MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 33.4 on the Noometry Index.

### Is Grok-2 (Dec 2024) or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 32.9 in the Noometry coding category.

### How many benchmarks do Grok-2 (Dec 2024) and MiniMax-M2.5 share?

18 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and MiniMax-M2.5 has 33.