# GLM-4.6 vs MiniMax-M2.7

> GLM-4.6 is the stronger model overall, scoring 40.9 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 1.9× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-minimax-m2-7
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and MiniMax-M2.7 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.6 leads 36.4 to 24.9.
- The biggest single-benchmark swing is Terminal-Bench: 24.5% for GLM-4.6 and 45.1% for MiniMax-M2.7.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.

## Snapshot

| | GLM-4.6 | MiniMax-M2.7 |
|---|---|---|
| Provider | Z.ai (Zhipu) | MiniMax |
| Noometry Index | 40.9 | 37.4 |
| Rank | 132 | 188 |
| Context | 205K | 205K |
| Input $/M | $0.60 | $0.30 |
| Output $/M | $2.20 | $1.20 |
| Weights | Open | Open |

## Coding

- GLM-4.6: 39.9 (#137)
- MiniMax-M2.7: 41.4 (#115)

| Benchmark | GLM-4.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena WebDev | 1339 | 1397 |
| SciCode | 38.4% | 47% |
| LMArena Coding | 1449 | 1454 |
| ALE-Bench | 340.82 | 599.25 |
| SWE-bench Verified (bash only) | 55.4% | — |
| WeirdML | — | 37% |

## Agentic & Tool Use

- GLM-4.6: 32.1 (#60)
- MiniMax-M2.7: 24.9 (#103)

| Benchmark | GLM-4.6 | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | 24.5% | 45.1% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |

## Reasoning

- GLM-4.6: 23.1 (#168)
- MiniMax-M2.7: 19.0 (#248)

| Benchmark | GLM-4.6 | MiniMax-M2.7 |
|---|---|---|
| CritPt | 1.1% | 0.6% |
| LMArena Hard Prompts | 1440 | 1422 |
| Kagi LLM Benchmark | 47.4% | — |
| NYT Connections (extended) | — | 24.7% |
| Thematic Generalization | — | 39.3% |
| Epoch Capabilities Index | — | 145.84 |

## Math

- GLM-4.6: 36.4 (#115)
- MiniMax-M2.7: 24.9 (#254)

| Benchmark | GLM-4.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1431 | 1420 |
| ProofBench | — | 3% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 39.6 (#118)
- MiniMax-M2.7: 37.1 (#151)

| Benchmark | GLM-4.6 | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 12.9% |
| LMArena Expert | 1432 | 1443 |

## Multilingual

- GLM-4.6: 53.6 (#62)
- MiniMax-M2.7: 50.5 (#120)

| Benchmark | GLM-4.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1426 | 1382 |
| LMArena Chinese | 1500 | 1439 |
| LMArena French | 1459 | 1422 |
| LMArena German | 1447 | 1398 |
| LMArena Japanese | 1394 | 1261 |
| LMArena Korean | 1401 | 1313 |
| LMArena Russian | 1418 | 1383 |
| LMArena Spanish | 1436 | 1403 |

## Instruction Following

- GLM-4.6: 74.5 (#93)
- MiniMax-M2.7: 74.2 (#101)

| Benchmark | GLM-4.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1404 |

## Long Context

- GLM-4.6: 43.4 (#91)
- MiniMax-M2.7: 43.3 (#94)

| Benchmark | GLM-4.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1423 | 1419 |

## Writing & Preference

- GLM-4.6: 61.3 (#86)
- MiniMax-M2.7: 59.1 (#107)

| Benchmark | GLM-4.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1440 | 1404 |
| LMArena Creative Writing | 1411 | 1354 |
| LMArena Multi-Turn | 1427 | 1413 |
| EQ-Bench Creative Writing | 1411 | — |

## FAQ

### Is GLM-4.6 better than MiniMax-M2.7?

GLM-4.6 is the stronger model overall, scoring 40.9 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 1.9× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.6 or MiniMax-M2.7?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.

### Is GLM-4.6 or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 39.9 in the Noometry coding category.

### Which has the bigger context window?

Both accept 205K tokens.

### How many benchmarks do GLM-4.6 and MiniMax-M2.7 share?

23 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and MiniMax-M2.7 has 30.