# MiniMax-M2.5 vs Qwen3-Coder 480B-A35B Instruct

> MiniMax-M2.5 and Qwen3-Coder 480B-A35B Instruct score almost the same on the Noometry Index (38.3 vs 38.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/minimax-m2-5-vs-qwen3-coder-480b-a35b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. MiniMax-M2.5 scores higher in 3 categories and Qwen3-Coder 480B-A35B Instruct in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 35.5.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 75.8% for MiniMax-M2.5 and 55.4% for Qwen3-Coder 480B-A35B Instruct.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 205K.

## Snapshot

| | MiniMax-M2.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.3 | 38.1 |
| Rank | 188 | 190 |
| Context | 205K | 262K |
| Input $/M | $0.30 | $1.50 |
| Output $/M | $1.20 | $7.50 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.5: 48.1 (#58)
- Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)

| Benchmark | MiniMax-M2.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 75.8% | 55.4% |
| LMArena WebDev | 1387 | 1275 |
| LMArena Coding | 1381 | 1412 |
| ALE-Bench | 618.17 | 461.45 |
| SWE-bench Multilingual | 68.3% | — |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| AlgoTune | — | 1.44 |

## Agentic & Tool Use

- MiniMax-M2.5: 30.4 (#77)
- Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)

| Benchmark | MiniMax-M2.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | 42.7% | 27.2% |
| Vending-Bench 2 | -23.16 | — |

## Reasoning

- MiniMax-M2.5: 17.5 (#292)
- Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)

| Benchmark | MiniMax-M2.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 55.2% | 49.5% |
| LMArena Hard Prompts | 1372 | 1372 |
| ARC-AGI-2 | 4.9% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Epoch Capabilities Index | 146.68 | — |

## Math

- MiniMax-M2.5: 26.9 (#253)
- Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)

| Benchmark | MiniMax-M2.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1378 | 1365 |
| ProofBench | 4% | — |

## Knowledge

- MiniMax-M2.5: 39.2 (#135)
- Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)

| Benchmark | MiniMax-M2.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1379 | 1338 |
| Vectara Hallucination Rate | 9.1% | — |

## Multilingual

- MiniMax-M2.5: 47.1 (#152)
- Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)

| Benchmark | MiniMax-M2.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1338 | 1346 |
| LMArena Chinese | 1393 | 1357 |
| LMArena French | 1362 | 1398 |
| LMArena German | 1362 | 1325 |
| LMArena Japanese | 1171 | 1310 |
| LMArena Korean | 1232 | 1305 |
| LMArena Russian | 1358 | 1366 |
| LMArena Spanish | 1354 | 1360 |

## Instruction Following

- MiniMax-M2.5: 71.5 (#148)
- Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)

| Benchmark | MiniMax-M2.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1353 | 1355 |

## Long Context

- MiniMax-M2.5: 37.5 (#216)
- Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)

| Benchmark | MiniMax-M2.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1366 | 1378 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |

## Writing & Preference

- MiniMax-M2.5: 53.9 (#153)
- Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)

| Benchmark | MiniMax-M2.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1359 | 1357 |
| LMArena Creative Writing | 1331 | 1333 |
| LMArena Multi-Turn | 1364 | 1365 |
| EQ-Bench Creative Writing | 1361 | — |

## FAQ

### Is MiniMax-M2.5 better than Qwen3-Coder 480B-A35B Instruct?

MiniMax-M2.5 and Qwen3-Coder 480B-A35B Instruct score almost the same on the Noometry Index (38.3 vs 38.1), so choose on price, context window or the category you care about most.

### Which is cheaper, MiniMax-M2.5 or Qwen3-Coder 480B-A35B Instruct?

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.

### Is MiniMax-M2.5 or Qwen3-Coder 480B-A35B Instruct better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 35.5 in the Noometry coding category.

### Which has the bigger context window?

Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 205K.

### How many benchmarks do MiniMax-M2.5 and Qwen3-Coder 480B-A35B Instruct share?

22 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.