# GLM-5.2 vs Qwen2.5 72B Instruct

> GLM-5.2 is the stronger model overall, scoring 50.9 to 31.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-2-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. GLM-5.2 scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.4 to 18.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.4% for GLM-5.2 and 8.1% for Qwen2.5 72B Instruct.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- GLM-5.2 accepts more context: 1M tokens versus 131K.

## Snapshot

| | GLM-5.2 | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 50.9 | 31.5 |
| Rank | 38 | 259 |
| Context | 1M | 131K |
| Input $/M | $1.40 | $1.40 |
| Output $/M | $4.40 | $5.60 |
| Weights | Open | Open |

## Coding

- GLM-5.2: 50.9 (#37)
- Qwen2.5 72B Instruct: 32.8 (#256)

| Benchmark | GLM-5.2 | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 70.1% | 16% |
| LMArena Coding | 1484 | 1293 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| LMArena WebDev | 1604 | — |
| SciCode | 50.5% | — |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 1,047 | — |

## Agentic & Tool Use

- GLM-5.2: 31.6 (#63)
- Qwen2.5 72B Instruct: 22.0 (#124)

| Benchmark | GLM-5.2 | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| BALROG | — | 16.2% |
| GBAEval | 0% | — |
| METR Time Horizons | — | 35.8% |
| Vending-Bench 2 | 8,314 | — |

## Reasoning

- GLM-5.2: 42.1 (#46)
- Qwen2.5 72B Instruct: 21.4 (#197)

| Benchmark | GLM-5.2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1480 | 1271 |
| DTBench | 93.6% | 62.9% |
| LMCA | 45.8% | 13.4% |
| Epoch Capabilities Index | 151.76 | 129.01 |
| 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% | — |
| Mystery Game Puzzles | 19% | — |
| Surface Evolver Bench | 55.6% | — |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- GLM-5.2: 55.4 (#35)
- Qwen2.5 72B Instruct: 18.1 (#281)

| Benchmark | GLM-5.2 | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.4% | 8.1% |
| LMArena Math | 1482 | 1283 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |

## Knowledge

- GLM-5.2: 57.1 (#36)
- Qwen2.5 72B Instruct: 26.9 (#247)

| Benchmark | GLM-5.2 | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 91.9% | 49.1% |
| LMArena Expert | 1484 | 1245 |
| SimpleQA Verified | 34.2% | — |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- GLM-5.2: 56.0 (#25)
- Qwen2.5 72B Instruct: 41.2 (#208)

| Benchmark | GLM-5.2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1459 | 1252 |
| LMArena Chinese | 1518 | 1272 |
| LMArena French | 1476 | 1279 |
| LMArena German | 1470 | 1234 |
| LMArena Japanese | 1451 | 1180 |
| LMArena Korean | 1445 | 1188 |
| LMArena Russian | 1467 | 1264 |
| LMArena Spanish | 1477 | 1255 |

## Instruction Following

- GLM-5.2: 77.1 (#32)
- Qwen2.5 72B Instruct: 65.7 (#216)

| Benchmark | GLM-5.2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1465 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- GLM-5.2: 45.3 (#43)
- Qwen2.5 72B Instruct: 38.9 (#183)

| Benchmark | GLM-5.2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1479 | 1282 |

## Writing & Preference

- GLM-5.2: 70.7 (#20)
- Qwen2.5 72B Instruct: 46.9 (#210)

| Benchmark | GLM-5.2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1470 | 1269 |
| LMArena Creative Writing | 1465 | 1221 |
| LMArena Multi-Turn | 1468 | 1272 |
| EQ-Bench Creative Writing | 1757 | — |
| WildBench | — | 80.2% |
| EQ-Bench 4 | 1222 | — |

## FAQ

### Is GLM-5.2 better than Qwen2.5 72B Instruct?

GLM-5.2 is the stronger model overall, scoring 50.9 to 31.5 on the Noometry Index.

### Which is cheaper, GLM-5.2 or Qwen2.5 72B Instruct?

GLM-5.2 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

### Is GLM-5.2 or Qwen2.5 72B Instruct better for coding?

GLM-5.2 scores higher on coding benchmarks: 50.9 versus 32.8 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.2 does, with 1M tokens against 131K.

### How many benchmarks do GLM-5.2 and Qwen2.5 72B Instruct share?

23 benchmarks have published results for both models. GLM-5.2 has 50 scored results on Noometry and Qwen2.5 72B Instruct has 43.