# GLM-5 vs MiniMax-M2.5

> GLM-5 is the stronger model overall, scoring 45.9 to 38.1 on the Noometry Index. MiniMax-M2.5 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-m2-5
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. GLM-5 scores higher in 9 categories and MiniMax-M2.5 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5 leads 44.8 to 25.8.
- The biggest single-benchmark swing is NYT Connections (extended): 74.8% for GLM-5 and 16.8% for MiniMax-M2.5.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1 / $3.20 for GLM-5.

## Snapshot

| | GLM-5 | MiniMax-M2.5 |
|---|---|---|
| Provider | Z.ai (Zhipu) | MiniMax |
| Noometry Index | 45.9 | 38.1 |
| Rank | 59 | 181 |
| Context | 205K | 205K |
| Input $/M | $1 | $0.30 |
| Output $/M | $3.20 | $1.20 |
| Weights | Open | Open |

## Coding

- GLM-5: 49.0 (#47)
- MiniMax-M2.5: 47.9 (#53)

| Benchmark | GLM-5 | MiniMax-M2.5 |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | 75.8% |
| LMArena WebDev | 1434 | 1386 |
| SWE-bench Multilingual | 69.7% | 68.3% |
| LMArena Coding | 1461 | 1380 |
| ALE-Bench | 765.62 | 618.17 |
| SWE-bench Verified | 72.1% | — |
| WeirdML | 48.2% | — |

## Agentic & Tool Use

- GLM-5: 30.9 (#65)
- MiniMax-M2.5: 30.2 (#70)

| Benchmark | GLM-5 | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | 52.4% | 42.7% |
| Vending-Bench 2 | 4,432 | -23.16 |
| 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 (#100)
- MiniMax-M2.5: 17.6 (#281)

| Benchmark | GLM-5 | MiniMax-M2.5 |
|---|---|---|
| ARC-AGI-2 | 4.9% | 4.9% |
| Kagi LLM Benchmark | 75% | 55.2% |
| NYT Connections (extended) | 74.8% | 16.8% |
| ARC-AGI-1 | 44.7% | 63.7% |
| LMArena Hard Prompts | 1451 | 1372 |
| Epoch Capabilities Index | 145.84 | 146.68 |
| SimpleBench | 53.2% | — |
| Chess Puzzles | 10% | — |
| ForecastBench | 61 | — |

## Math

- GLM-5: 44.8 (#66)
- MiniMax-M2.5: 25.8 (#242)

| Benchmark | GLM-5 | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1440 | 1378 |
| MathArena Final-Answer Competitions | 65.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| ProofBench | — | 4% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-5: 52.2 (#59)
- MiniMax-M2.5: 38.6 (#132)

| Benchmark | GLM-5 | MiniMax-M2.5 |
|---|---|---|
| Vectara Hallucination Rate | 10.1% | 9.1% |
| LMArena Expert | 1454 | 1378 |
| GPQA Diamond | 87.8% | — |

## Multilingual

- GLM-5: 53.9 (#57)
- MiniMax-M2.5: 47.3 (#147)

| Benchmark | GLM-5 | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1430 | 1338 |
| LMArena Chinese | 1511 | 1392 |
| LMArena French | 1455 | 1363 |
| LMArena German | 1445 | 1361 |
| LMArena Japanese | 1416 | 1169 |
| LMArena Korean | 1421 | 1232 |
| LMArena Russian | 1436 | 1359 |
| LMArena Spanish | 1452 | 1354 |

## Instruction Following

- GLM-5: 75.4 (#64)
- MiniMax-M2.5: 71.7 (#143)

| Benchmark | GLM-5 | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1427 | 1353 |

## Long Context

- GLM-5: 44.6 (#58)
- MiniMax-M2.5: 37.4 (#211)

| Benchmark | GLM-5 | MiniMax-M2.5 |
|---|---|---|
| CL-bench | 18.7% | 11.4% |
| LMArena Longer Query | 1446 | 1367 |
| CL-bench Life | — | 6.3% |

## Writing & Preference

- GLM-5: 66.2 (#38)
- MiniMax-M2.5: 54.1 (#149)

| Benchmark | GLM-5 | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1446 | 1359 |
| LMArena Creative Writing | 1438 | 1331 |
| EQ-Bench Creative Writing | 1601 | 1361 |
| LMArena Multi-Turn | 1456 | 1364 |

## FAQ

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

GLM-5 is the stronger model overall, scoring 45.9 to 38.1 on the Noometry Index. MiniMax-M2.5 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-M2.5?

MiniMax-M2.5 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-M2.5 better for coding?

GLM-5 scores higher on coding benchmarks: 49.0 versus 47.9 in the Noometry coding category.

### Which has the bigger context window?

Both accept 205K tokens.

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

31 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and MiniMax-M2.5 has 33.