# GLM-5 vs MiniMax-M2

> GLM-5 is the stronger model overall, scoring 46.1 to 37.4 on the Noometry Index. MiniMax-M2 costs 3.0× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-vs-minimax-m2
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GLM-5 scores higher in 9 categories and MiniMax-M2 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 37.0.
- The biggest single-benchmark swing is NYT Connections (extended): 74.8% for GLM-5 and 14.8% for MiniMax-M2.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1 / $3.20 for GLM-5.

## Snapshot

| | GLM-5 | MiniMax-M2 |
|---|---|---|
| Provider | Z.ai (Zhipu) | MiniMax |
| Noometry Index | 46.1 | 37.4 |
| Rank | 66 | 204 |
| Context | 205K | 205K |
| Input $/M | $1 | $0.30 |
| Output $/M | $3.20 | $1.20 |
| Weights | Open | Open |

## Coding

- GLM-5: 49.0 (#52)
- MiniMax-M2: 39.3 (#159)

| Benchmark | GLM-5 | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | 61% |
| LMArena WebDev | 1434 | 1297 |
| LMArena Coding | 1461 | 1370 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Multilingual | 69.7% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 765.62 | — |

## Agentic & Tool Use

- GLM-5: 31.1 (#71)
- MiniMax-M2: 25.1 (#109)

| Benchmark | GLM-5 | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | 52.4% | 30% |
| Vending-Bench 2 | 4,432 | 160.6 |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |

## Reasoning

- GLM-5: 27.6 (#116)
- MiniMax-M2: 19.4 (#258)

| Benchmark | GLM-5 | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 75% | 57.8% |
| NYT Connections (extended) | 74.8% | 14.8% |
| LMArena Hard Prompts | 1452 | 1357 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| ARC-AGI-1 | 44.7% | — |
| Chess Puzzles | 10% | — |
| Epoch Capabilities Index | 145.83 | — |
| ForecastBench | 61 | — |

## Math

- GLM-5: 46.4 (#71)
- MiniMax-M2: 37.3 (#160)

| Benchmark | GLM-5 | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1440 | 1352 |
| MathArena Final-Answer Competitions | 65.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-5: 52.3 (#64)
- MiniMax-M2: 37.0 (#163)

| Benchmark | GLM-5 | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1454 | 1337 |
| GPQA Diamond | 87.8% | — |
| Vectara Hallucination Rate | 10.1% | — |

## Multilingual

- GLM-5: 53.7 (#58)
- MiniMax-M2: 45.3 (#171)

| Benchmark | GLM-5 | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1430 | 1313 |
| LMArena Chinese | 1511 | 1366 |
| LMArena French | 1455 | 1335 |
| LMArena German | 1445 | 1355 |
| LMArena Russian | 1436 | 1331 |
| LMArena Spanish | 1454 | 1326 |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1423 | — |

## Instruction Following

- GLM-5: 75.2 (#67)
- MiniMax-M2: 70.2 (#166)

| Benchmark | GLM-5 | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1428 | 1328 |

## Long Context

- GLM-5: 44.7 (#60)
- MiniMax-M2: 40.5 (#153)

| Benchmark | GLM-5 | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1446 | 1331 |
| CL-bench | 18.7% | — |

## Writing & Preference

- GLM-5: 66.0 (#38)
- MiniMax-M2: 53.0 (#162)

| Benchmark | GLM-5 | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1446 | 1340 |
| LMArena Creative Writing | 1439 | 1286 |
| LMArena Multi-Turn | 1456 | 1361 |
| EQ-Bench Creative Writing | 1601 | — |

## FAQ

### Is GLM-5 better than MiniMax-M2?

GLM-5 is the stronger model overall, scoring 46.1 to 37.4 on the Noometry Index. MiniMax-M2 costs 3.0× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.

### Which is cheaper, GLM-5 or MiniMax-M2?

MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GLM-5 lists at $1 and $3.20.

### Is GLM-5 or MiniMax-M2 better for coding?

GLM-5 scores higher on coding benchmarks: 49.0 versus 39.3 in the Noometry coding category.

### Which has the bigger context window?

Both accept 205K tokens.

### How many benchmarks do GLM-5 and MiniMax-M2 share?

21 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and MiniMax-M2 has 21.