# GLM-5.2 vs Qwen2.5-Max

> GLM-5.2 is the stronger model overall, scoring 50.9 to 40.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-2-vs-qwen2-5-max
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.2 leads 57.1 to 34.8.
- GLM-5.2 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.2 | Qwen2.5-Max |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 50.9 | 40.1 |
| Rank | 38 | 142 |
| Context | 1M | — |
| Input $/M | $1.40 | — |
| Output $/M | $4.40 | — |
| Weights | Open | Proprietary |

## Coding

- GLM-5.2: 50.9 (#37)
- Qwen2.5-Max: 41.2 (#118)

| Benchmark | GLM-5.2 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1484 | 1359 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| LMArena WebDev | 1604 | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 1,047 | — |

## Agentic & Tool Use

- GLM-5.2: 31.6 (#63)
- Qwen2.5-Max: —

| Benchmark | GLM-5.2 | Qwen2.5-Max |
|---|---|---|
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |

## Reasoning

- GLM-5.2: 42.1 (#46)
- Qwen2.5-Max: 24.6 (#144)

| Benchmark | GLM-5.2 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1480 | 1360 |
| Epoch Capabilities Index | 151.76 | 132.54 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| NYT Connections (extended) | 74.3% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| Chess Puzzles | 21% | — |
| EBR-Bench | 9.5% | — |
| LiveBench Reasoning | — | 51.4% |
| Mystery Game Puzzles | 19% | — |
| DTBench | 93.6% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |
| LiveBench | — | 62.3% |

## Math

- GLM-5.2: 55.4 (#35)
- Qwen2.5-Max: 34.3 (#162)

| Benchmark | GLM-5.2 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1482 | 1369 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| OTIS Mock AIME 2024-2025 | 86.4% | — |
| ProofBench | 35% | — |
| LiveBench Math | — | 58.4% |

## Knowledge

- GLM-5.2: 57.1 (#36)
- Qwen2.5-Max: 34.8 (#181)

| Benchmark | GLM-5.2 | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1484 | 1337 |
| GPQA Diamond | 91.9% | — |
| SimpleQA Verified | 34.2% | — |
| Confabulations | — | 21.8% |

## Multilingual

- GLM-5.2: 56.0 (#25)
- Qwen2.5-Max: 48.3 (#140)

| Benchmark | GLM-5.2 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1459 | 1352 |
| LMArena Chinese | 1518 | 1382 |
| LMArena French | 1476 | 1396 |
| LMArena German | 1470 | 1350 |
| LMArena Japanese | 1451 | 1299 |
| LMArena Korean | 1445 | 1304 |
| LMArena Russian | 1467 | 1353 |
| LMArena Spanish | 1477 | 1377 |

## Instruction Following

- GLM-5.2: 77.1 (#32)
- Qwen2.5-Max: 71.5 (#147)

| Benchmark | GLM-5.2 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1465 | 1335 |
| LiveBench Instruction Following | — | 75.3% |

## Long Context

- GLM-5.2: 45.3 (#43)
- Qwen2.5-Max: 41.3 (#137)

| Benchmark | GLM-5.2 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1479 | 1358 |

## Writing & Preference

- GLM-5.2: 70.7 (#20)
- Qwen2.5-Max: 55.6 (#141)

| Benchmark | GLM-5.2 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1470 | 1367 |
| LMArena Creative Writing | 1465 | 1339 |
| LMArena Multi-Turn | 1468 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
| LiveBench Language | — | 56.3% |

## FAQ

### Is GLM-5.2 better than Qwen2.5-Max?

GLM-5.2 is the stronger model overall, scoring 50.9 to 40.1 on the Noometry Index.

### Is GLM-5.2 or Qwen2.5-Max better for coding?

GLM-5.2 scores higher on coding benchmarks: 50.9 versus 41.2 in the Noometry coding category.

### How many benchmarks do GLM-5.2 and Qwen2.5-Max share?

18 benchmarks have published results for both models. GLM-5.2 has 50 scored results on Noometry and Qwen2.5-Max has 27.