# MiMo-V2.6-Pro vs Qwen3 Max

> MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 43.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-6-pro-vs-qwen3-max
- Last updated: 2026-10-11
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 7 categories and Qwen3 Max in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Pro leads 43.1 to 22.6.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 262K.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.

## Snapshot

| | MiMo-V2.6-Pro | Qwen3 Max |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 50.3 | 43.7 |
| Rank | 49 | 87 |
| Context | 1.05M | 262K |
| Input $/M | $0.43 | $1.20 |
| Output $/M | $0.87 | $6 |
| Weights | Open | Proprietary |

## Coding

- MiMo-V2.6-Pro: 55.5 (#23)
- Qwen3 Max: 43.0 (#93)

| Benchmark | MiMo-V2.6-Pro | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1534 | 1456 |
| ALE-Bench | 1,158 | 370.45 |
| LMArena WebDev | 1629 | — |
| SciCode | 60.9% | — |

## Agentic & Tool Use

- MiMo-V2.6-Pro: 37.5 (#35)
- Qwen3 Max: —

| Benchmark | MiMo-V2.6-Pro | Qwen3 Max |
|---|---|---|
| APEX-Agents | 59.5% | — |
| Vending-Bench 2 | — | 71.56 |

## Reasoning

- MiMo-V2.6-Pro: 43.1 (#50)
- Qwen3 Max: 22.6 (#190)

| Benchmark | MiMo-V2.6-Pro | Qwen3 Max |
|---|---|---|
| LMArena Hard Prompts | 1512 | 1448 |
| Kagi LLM Benchmark | — | 72.5% |
| NYT Connections (extended) | — | 30.1% |
| CritPt | 26.6% | — |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LMCA | — | 28.3% |
| Epoch Capabilities Index | — | 142.38 |

## Math

- MiMo-V2.6-Pro: 54.5 (#45)
- Qwen3 Max: 38.7 (#131)

| Benchmark | MiMo-V2.6-Pro | Qwen3 Max |
|---|---|---|
| LMArena Math | 1494 | 1446 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| ProofBench | 70% | — |
| MATH Level 5 | — | 97.1% |

## Knowledge

- MiMo-V2.6-Pro: 43.5 (#92)
- Qwen3 Max: 48.1 (#78)

| Benchmark | MiMo-V2.6-Pro | Qwen3 Max |
|---|---|---|
| LMArena Expert | 1543 | 1455 |
| GPQA Diamond | — | 72.6% |
| SimpleQA Verified | — | 48.7% |

## Multimodal

- MiMo-V2.6-Pro: 40.8 (#43)
- Qwen3 Max: —

| Benchmark | MiMo-V2.6-Pro | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1264 | — |

## Multilingual

- MiMo-V2.6-Pro: 56.9 (#14)
- Qwen3 Max: 53.7 (#62)

| Benchmark | MiMo-V2.6-Pro | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1474 | 1429 |
| LMArena Chinese | 1529 | 1478 |
| LMArena Russian | 1480 | 1428 |
| LMArena French | — | 1449 |
| LMArena German | — | 1463 |
| LMArena Japanese | — | 1397 |
| LMArena Korean | — | 1399 |
| LMArena Spanish | — | 1462 |

## Instruction Following

- MiMo-V2.6-Pro: 78.2 (#12)
- Qwen3 Max: 74.8 (#87)

| Benchmark | MiMo-V2.6-Pro | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1493 | 1419 |

## Long Context

- MiMo-V2.6-Pro: 46.0 (#27)
- Qwen3 Max: 41.6 (#134)

| Benchmark | MiMo-V2.6-Pro | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1501 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |

## Writing & Preference

- MiMo-V2.6-Pro: 66.8 (#33)
- Qwen3 Max: 62.4 (#76)

| Benchmark | MiMo-V2.6-Pro | Qwen3 Max |
|---|---|---|
| LMArena Text | 1492 | 1439 |
| LMArena Creative Writing | 1468 | 1402 |
| LMArena Multi-Turn | 1464 | 1446 |

## FAQ

### Is MiMo-V2.6-Pro better than Qwen3 Max?

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 43.7 on the Noometry Index.

### Which is cheaper, MiMo-V2.6-Pro or Qwen3 Max?

MiMo-V2.6-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Qwen3 Max lists at $1.20 and $6.

### Is MiMo-V2.6-Pro or Qwen3 Max better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 43.0 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.6-Pro does, with 1.05M tokens against 262K.

### How many benchmarks do MiMo-V2.6-Pro and Qwen3 Max share?

13 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Qwen3 Max has 33.