# Grok-3 mini vs MiniMax-M2.5

> Grok-3 mini is the stronger model overall, scoring 41.0 to 38.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-minimax-m2-5
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Grok-3 mini scores higher in 5 categories and MiniMax-M2.5 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-3 mini leads 40.3 to 25.8.
- The biggest single-benchmark swing is ARC-AGI-1: 16.5% for Grok-3 mini and 63.7% for MiniMax-M2.5.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-3 mini | MiniMax-M2.5 |
|---|---|---|
| Provider | xAI | MiniMax |
| Noometry Index | 41.0 | 38.1 |
| Rank | 130 | 181 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Grok-3 mini: 40.4 (#126)
- MiniMax-M2.5: 47.9 (#53)

| Benchmark | Grok-3 mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1380 | 1380 |
| SWE-bench Verified (bash only) | — | 75.8% |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1386 |
| SWE-bench Multilingual | — | 68.3% |
| WeirdML | 42.6% | — |
| ALE-Bench | — | 618.17 |

## Agentic & Tool Use

- Grok-3 mini: —
- MiniMax-M2.5: 30.2 (#70)

| Benchmark | Grok-3 mini | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |

## Reasoning

- Grok-3 mini: 13.8 (#323)
- MiniMax-M2.5: 17.6 (#281)

| Benchmark | Grok-3 mini | MiniMax-M2.5 |
|---|---|---|
| ARC-AGI-2 | 0.4% | 4.9% |
| Kagi LLM Benchmark | 61.3% | 55.2% |
| ARC-AGI-1 | 16.5% | 63.7% |
| LMArena Hard Prompts | 1374 | 1372 |
| Epoch Capabilities Index | 140.35 | 146.68 |
| NYT Connections (extended) | — | 16.8% |

## Math

- Grok-3 mini: 40.3 (#78)
- MiniMax-M2.5: 25.8 (#242)

| Benchmark | Grok-3 mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1386 | 1378 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| ProofBench | — | 4% |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |

## Knowledge

- Grok-3 mini: 46.3 (#75)
- MiniMax-M2.5: 38.6 (#132)

| Benchmark | Grok-3 mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1395 | 1378 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| Vectara Hallucination Rate | — | 9.1% |
| GPQA (HELM) | 67.5% | — |

## Multilingual

- Grok-3 mini: 48.3 (#141)
- MiniMax-M2.5: 47.3 (#147)

| Benchmark | Grok-3 mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1352 | 1338 |
| LMArena Chinese | 1387 | 1392 |
| LMArena French | 1357 | 1363 |
| LMArena German | 1350 | 1361 |
| LMArena Japanese | 1343 | 1169 |
| LMArena Korean | 1336 | 1232 |
| LMArena Russian | 1352 | 1359 |
| LMArena Spanish | 1379 | 1354 |

## Instruction Following

- Grok-3 mini: 78.7 (#8)
- MiniMax-M2.5: 71.7 (#143)

| Benchmark | Grok-3 mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1356 | 1353 |
| IFEval | 95.1% | — |

## Long Context

- Grok-3 mini: 41.0 (#142)
- MiniMax-M2.5: 37.4 (#211)

| Benchmark | Grok-3 mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1372 | 1367 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |

## Writing & Preference

- Grok-3 mini: 52.7 (#163)
- MiniMax-M2.5: 54.1 (#149)

| Benchmark | Grok-3 mini | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1370 | 1359 |
| LMArena Creative Writing | 1342 | 1331 |
| LMArena Multi-Turn | 1355 | 1364 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | — | 1361 |
| WildBench | 65.1% | — |

## FAQ

### Is Grok-3 mini better than MiniMax-M2.5?

Grok-3 mini is the stronger model overall, scoring 41.0 to 38.1 on the Noometry Index.

### Is Grok-3 mini or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 40.4 in the Noometry coding category.

### How many benchmarks do Grok-3 mini and MiniMax-M2.5 share?

21 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and MiniMax-M2.5 has 33.