# Grok 4.6 vs MiMo-V2-Pro

> Grok 4.6 is the stronger model overall, scoring 56.9 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 5.5× 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-mimo-v2-pro
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Grok 4.6 scores higher in 6 categories and MiMo-V2-Pro in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 22.1.
- The biggest single-benchmark swing is NYT Connections (extended): 80% for Grok 4.6 and 25.8% for MiMo-V2-Pro.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2 / $6 for Grok 4.6.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 500K.

## Snapshot

| | Grok 4.6 | MiMo-V2-Pro |
|---|---|---|
| Provider | xAI | Xiaomi |
| Noometry Index | 56.9 | 43.0 |
| Rank | 21 | 103 |
| Context | 500K | 1.05M |
| Input $/M | $2 | $0.43 |
| Output $/M | $6 | $0.87 |
| Weights | Proprietary | Proprietary |

## Coding

- Grok 4.6: 58.5 (#16)
- MiMo-V2-Pro: 43.8 (#83)

| Benchmark | Grok 4.6 | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1617 | 1433 |
| LMArena Coding | 1465 | 1476 |
| ALE-Bench | 1,508 | 785.17 |
| DeepSWE | 67.5% | — |
| FrontierCode | 48% | — |
| CursorBench | 41.4% | — |
| FrontierSWE | 25.3% | — |
| SciCode | 56.5% | — |
| WeirdML | 67.3% | — |

## Agentic & Tool Use

- Grok 4.6: 39.4 (#27)
- MiMo-V2-Pro: —

| Benchmark | Grok 4.6 | MiMo-V2-Pro |
|---|---|---|
| APEX-Agents | 65.3% | — |
| GDP.pdf | 17.2% | — |
| Vending-Bench 2 | 9,047 | — |

## Reasoning

- Grok 4.6: 61.4 (#20)
- MiMo-V2-Pro: 22.1 (#206)

| Benchmark | Grok 4.6 | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | 80% | 25.8% |
| LMArena Hard Prompts | 1447 | 1457 |
| ARC-AGI-2 | 67.1% | — |
| SimpleBench | 75.9% | — |
| ARC-AGI-1 | 87.5% | — |
| CritPt | 19.7% | — |
| Chess Puzzles | 40% | — |
| Thematic Generalization | — | 45.9% |
| EBR-Bench | 30.5% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.3% | — |
| LMCA | 48.5% | — |
| Epoch Capabilities Index | 156.44 | — |

## Math

- Grok 4.6: 67.0 (#24)
- MiMo-V2-Pro: 39.5 (#102)

| Benchmark | Grok 4.6 | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1423 | 1447 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |
| OTIS Mock AIME 2024-2025 | 99.2% | — |
| ProofBench | 51% | — |

## Knowledge

- Grok 4.6: 63.3 (#20)
- MiMo-V2-Pro: 41.4 (#111)

| Benchmark | Grok 4.6 | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1467 | 1478 |
| GPQA Diamond | 94% | — |
| SimpleQA Verified | 49.3% | — |

## Multimodal

- Grok 4.6: 43.6 (#23)
- MiMo-V2-Pro: —

| Benchmark | Grok 4.6 | MiMo-V2-Pro |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |

## Multilingual

- Grok 4.6: 53.0 (#74)
- MiMo-V2-Pro: 52.7 (#81)

| Benchmark | Grok 4.6 | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1420 | 1416 |
| LMArena Chinese | 1480 | 1456 |
| LMArena French | 1461 | 1469 |
| LMArena German | 1431 | 1417 |
| LMArena Japanese | 1376 | 1366 |
| LMArena Korean | 1397 | 1400 |
| LMArena Russian | 1422 | 1427 |
| LMArena Spanish | 1404 | 1457 |

## Instruction Following

- Grok 4.6: 75.4 (#63)
- MiMo-V2-Pro: 76.0 (#49)

| Benchmark | Grok 4.6 | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1431 | 1445 |

## Long Context

- Grok 4.6: 44.5 (#66)
- MiMo-V2-Pro: 41.5 (#138)

| Benchmark | Grok 4.6 | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1454 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |

## Writing & Preference

- Grok 4.6: 62.3 (#80)
- MiMo-V2-Pro: 62.8 (#70)

| Benchmark | Grok 4.6 | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1428 | 1436 |
| LMArena Creative Writing | 1428 | 1415 |
| LMArena Multi-Turn | 1425 | 1456 |

## FAQ

### Is Grok 4.6 better than MiMo-V2-Pro?

Grok 4.6 is the stronger model overall, scoring 56.9 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 5.5× 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 MiMo-V2-Pro?

MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Grok 4.6 lists at $2 and $6.

### Is Grok 4.6 or MiMo-V2-Pro better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 43.8 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2-Pro does, with 1.05M tokens against 500K.

### How many benchmarks do Grok 4.6 and MiMo-V2-Pro share?

20 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and MiMo-V2-Pro has 23.