# GLM-4.6 vs MiMo-V2.5-Pro

> MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 41.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-mimo-v2-5-pro
- Last updated: 2026-10-11
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. GLM-4.6 scores higher in 0 categories and MiMo-V2.5-Pro in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.5-Pro leads 47.4 to 40.1.
- The biggest single-benchmark swing is SciCode: 38.4% for GLM-4.6 and 50.2% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 205K.

## Snapshot

| | GLM-4.6 | MiMo-V2.5-Pro |
|---|---|---|
| Provider | Z.ai (Zhipu) | Xiaomi |
| Noometry Index | 41.4 | 45.2 |
| Rank | 135 | 74 |
| Context | 205K | 1.05M |
| Input $/M | $0.60 | $0.43 |
| Output $/M | $2.20 | $0.87 |
| Weights | Open | Open |

## Coding

- GLM-4.6: 40.1 (#148)
- MiMo-V2.5-Pro: 47.4 (#60)

| Benchmark | GLM-4.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | 1340 | 1479 |
| SciCode | 38.4% | 50.2% |
| LMArena Coding | 1449 | 1503 |
| ALE-Bench | 340.82 | 899.8 |
| SWE-bench Verified (bash only) | 55.4% | — |

## Agentic & Tool Use

- GLM-4.6: 32.3 (#66)
- MiMo-V2.5-Pro: —

| Benchmark | GLM-4.6 | MiMo-V2.5-Pro |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |

## Reasoning

- GLM-4.6: 23.7 (#172)
- MiMo-V2.5-Pro: 26.8 (#130)

| Benchmark | GLM-4.6 | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 1.1% | 4% |
| LMArena Hard Prompts | 1440 | 1488 |
| Kagi LLM Benchmark | 47.4% | — |
| NYT Connections (extended) | — | 34.4% |
| DTBench | — | 84.5% |
| LMCA | — | 29.5% |

## Math

- GLM-4.6: 39.1 (#111)
- MiMo-V2.5-Pro: 40.0 (#96)

| Benchmark | GLM-4.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1432 | 1481 |
| ProofBench | — | 22% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 40.2 (#124)
- MiMo-V2.5-Pro: 42.2 (#98)

| Benchmark | GLM-4.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1431 | 1503 |
| Vectara Hallucination Rate | 9.5% | — |

## Multilingual

- GLM-4.6: 53.5 (#66)
- MiMo-V2.5-Pro: 55.1 (#34)

| Benchmark | GLM-4.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1426 | 1449 |
| LMArena Chinese | 1499 | 1507 |
| LMArena French | 1459 | 1488 |
| LMArena German | 1447 | 1458 |
| LMArena Japanese | 1393 | 1412 |
| LMArena Korean | 1400 | 1437 |
| LMArena Russian | 1419 | 1450 |
| LMArena Spanish | 1436 | 1471 |

## Instruction Following

- GLM-4.6: 74.3 (#98)
- MiMo-V2.5-Pro: 77.5 (#21)

| Benchmark | GLM-4.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1410 | 1477 |

## Long Context

- GLM-4.6: 43.4 (#94)
- MiMo-V2.5-Pro: 45.4 (#37)

| Benchmark | GLM-4.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1422 | 1483 |

## Writing & Preference

- GLM-4.6: 61.1 (#90)
- MiMo-V2.5-Pro: 65.3 (#49)

| Benchmark | GLM-4.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1440 | 1465 |
| LMArena Creative Writing | 1411 | 1440 |
| EQ-Bench Creative Writing | 1411 | 1493 |
| LMArena Multi-Turn | 1427 | 1477 |
| EQ-Bench 4 | — | 1208 |

## FAQ

### Is GLM-4.6 better than MiMo-V2.5-Pro?

MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 41.4 on the Noometry Index.

### Which is cheaper, GLM-4.6 or MiMo-V2.5-Pro?

MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.

### Is GLM-4.6 or MiMo-V2.5-Pro better for coding?

MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 40.1 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5-Pro does, with 1.05M tokens against 205K.

### How many benchmarks do GLM-4.6 and MiMo-V2.5-Pro share?

22 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and MiMo-V2.5-Pro has 27.