# GLM-4.5-Air vs MiniMax-M3

> MiniMax-M3 is the stronger model overall, scoring 43.8 to 38.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-5-air-vs-minimax-m3
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-4.5-Air scores higher in 0 categories and MiniMax-M3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 35.0.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 131K.

## Snapshot

| | GLM-4.5-Air | MiniMax-M3 |
|---|---|---|
| Provider | Z.ai (Zhipu) | MiniMax |
| Noometry Index | 38.9 | 43.8 |
| Rank | 177 | 85 |
| Context | 131K | 1M |
| Input $/M | $0.20 | $0.30 |
| Output $/M | $1.10 | $1.20 |
| Weights | Open | Open |

## Coding

- GLM-4.5-Air: 33.3 (#259)
- MiniMax-M3: 41.8 (#118)

| Benchmark | GLM-4.5-Air | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1397 | 1469 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| GSO | 2.9% | — |
| ALE-Bench | — | 640.02 |

## Agentic & Tool Use

- GLM-4.5-Air: —
- MiniMax-M3: 22.6 (#130)

| Benchmark | GLM-4.5-Air | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- GLM-4.5-Air: 24.1 (#166)
- MiniMax-M3: 30.1 (#87)

| Benchmark | GLM-4.5-Air | MiniMax-M3 |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1447 |
| ForecastBench | 59.2 | 61.4 |
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | 43% | — |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 146.95 |

## Math

- GLM-4.5-Air: 36.2 (#170)
- MiniMax-M3: 40.0 (#95)

| Benchmark | GLM-4.5-Air | MiniMax-M3 |
|---|---|---|
| LMArena Math | 1396 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |
| Omni-MATH | 39.1% | — |

## Knowledge

- GLM-4.5-Air: 35.0 (#191)
- MiniMax-M3: 58.4 (#35)

| Benchmark | GLM-4.5-Air | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1370 | 1461 |
| GPQA Diamond | — | 90.9% |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |

## Multimodal

- GLM-4.5-Air: —
- MiniMax-M3: 40.2 (#51)

| Benchmark | GLM-4.5-Air | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |

## Multilingual

- GLM-4.5-Air: 49.1 (#135)
- MiniMax-M3: 53.0 (#75)

| Benchmark | GLM-4.5-Air | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1366 | 1420 |
| LMArena Chinese | 1426 | 1463 |
| LMArena French | 1399 | 1447 |
| LMArena German | 1377 | 1426 |
| LMArena Japanese | 1348 | 1381 |
| LMArena Korean | 1308 | 1372 |
| LMArena Russian | 1373 | 1428 |
| LMArena Spanish | 1386 | 1432 |

## Instruction Following

- GLM-4.5-Air: 69.6 (#171)
- MiniMax-M3: 75.5 (#62)

| Benchmark | GLM-4.5-Air | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1354 | 1433 |
| IFEval | 81.2% | — |

## Long Context

- GLM-4.5-Air: 41.6 (#135)
- MiniMax-M3: 44.2 (#72)

| Benchmark | GLM-4.5-Air | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1366 | 1445 |

## Writing & Preference

- GLM-4.5-Air: 55.9 (#139)
- MiniMax-M3: 62.1 (#83)

| Benchmark | GLM-4.5-Air | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1384 | 1433 |
| LMArena Creative Writing | 1343 | 1404 |
| LMArena Multi-Turn | 1371 | 1442 |
| WildBench | 78.9% | — |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is GLM-4.5-Air better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 38.9 on the Noometry Index.

### Which is cheaper, GLM-4.5-Air or MiniMax-M3?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.

### Is GLM-4.5-Air or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 33.3 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 131K.

### How many benchmarks do GLM-4.5-Air and MiniMax-M3 share?

18 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and MiniMax-M3 has 41.