# MiniMax-M3 vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.0 to 43.5 on the Noometry Index. MiniMax-M3 costs 5.7× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/minimax-m3-vs-qwen3-8-max
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. MiniMax-M3 scores higher in 1 category and Qwen3.8 Max in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.1 to 39.1.
- The biggest single-benchmark swing is ProofBench: 18% for MiniMax-M3 and 58% for Qwen3.8 Max.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- MiniMax-M3 has downloadable open weights; the other is API-only.

## Snapshot

| | MiniMax-M3 | Qwen3.8 Max |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 43.5 | 56.0 |
| Rank | 81 | 21 |
| Context | 1M | 1M |
| Input $/M | $0.30 | $2 |
| Output $/M | $1.20 | $6 |
| Weights | Open | Proprietary |

## Coding

- MiniMax-M3: 41.5 (#111)
- Qwen3.8 Max: 52.3 (#30)

| Benchmark | MiniMax-M3 | Qwen3.8 Max |
|---|---|---|
| LMArena WebDev | 1482 | 1671 |
| SciCode | 47.1% | 52.9% |
| LMArena Coding | 1470 | 1499 |
| DeepSWE | — | 57.5% |
| FrontierCode | 14.7% | — |
| FrontierSWE | — | 15.8% |
| ALE-Bench | 640.02 | — |

## Agentic & Tool Use

- MiniMax-M3: 22.5 (#121)
- Qwen3.8 Max: 42.6 (#17)

| Benchmark | MiniMax-M3 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| τ²-bench Banking | — | 55.1% |
| GBAEval | 0.9% | — |
| GDP.pdf | — | 23.2% |
| Vending-Bench 2 | 2,158 | — |

## Reasoning

- MiniMax-M3: 29.3 (#83)
- Qwen3.8 Max: 53.4 (#26)

| Benchmark | MiniMax-M3 | Qwen3.8 Max |
|---|---|---|
| NYT Connections (extended) | 65.1% | 88.3% |
| CritPt | 3.7% | 20% |
| Chess Puzzles | 14% | 40% |
| LMArena Hard Prompts | 1447 | 1493 |
| Mystery Game Puzzles | 8% | 38% |
| DTBench | 78.9% | 92% |
| LMCA | 33.7% | 46.2% |
| Epoch Capabilities Index | 147 | 156.69 |
| SimpleBench | 45.8% | — |
| Surface Evolver Bench | 55% | — |
| ForecastBench | 61.4 | — |

## Math

- MiniMax-M3: 39.1 (#83)
- Qwen3.8 Max: 73.1 (#15)

| Benchmark | MiniMax-M3 | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 100% |
| ProofBench | 18% | 58% |
| LMArena Math | 1432 | 1498 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |

## Knowledge

- MiniMax-M3: 58.4 (#32)
- Qwen3.8 Max: 61.7 (#25)

| Benchmark | MiniMax-M3 | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 90.9% | 92.7% |
| LMArena Expert | 1462 | 1504 |
| SimpleQA Verified | — | 47.3% |

## Multimodal

- MiniMax-M3: 39.5 (#45)
- Qwen3.8 Max: 36.9 (#70)

| Benchmark | MiniMax-M3 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | 1254 | 1314 |
| Furniture Assembly | — | 20% |
| LMArena Document | 1435 | — |

## Multilingual

- MiniMax-M3: 53.2 (#70)
- Qwen3.8 Max: 56.6 (#18)

| Benchmark | MiniMax-M3 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1420 | 1468 |
| LMArena Chinese | 1465 | 1537 |
| LMArena French | 1445 | 1502 |
| LMArena German | 1424 | 1489 |
| LMArena Japanese | 1381 | 1466 |
| LMArena Korean | 1372 | 1467 |
| LMArena Russian | 1430 | 1478 |
| LMArena Spanish | 1431 | 1495 |

## Instruction Following

- MiniMax-M3: 75.7 (#56)
- Qwen3.8 Max: 77.7 (#19)

| Benchmark | MiniMax-M3 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1433 | 1478 |

## Long Context

- MiniMax-M3: 44.2 (#68)
- Qwen3.8 Max: 45.5 (#30)

| Benchmark | MiniMax-M3 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1445 | 1486 |

## Writing & Preference

- MiniMax-M3: 62.3 (#79)
- Qwen3.8 Max: 67.0 (#31)

| Benchmark | MiniMax-M3 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1433 | 1480 |
| LMArena Creative Writing | 1405 | 1478 |
| LMArena Multi-Turn | 1441 | 1487 |
| EQ-Bench 4 | 1150 | — |

## FAQ

### Is MiniMax-M3 better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.0 to 43.5 on the Noometry Index. MiniMax-M3 costs 5.7× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

### Which is cheaper, MiniMax-M3 or Qwen3.8 Max?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.8 Max lists at $2 and $6.

### Is MiniMax-M3 or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 41.5 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do MiniMax-M3 and Qwen3.8 Max share?

30 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Qwen3.8 Max has 38.