# GLM-5.2 vs Step 3

> GLM-5.2 is the stronger model overall, scoring 51.1 to 40.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-2-vs-step-3
- Last updated: 2026-10-11
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and Step 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.2 leads 57.1 to 36.8.

## Snapshot

| | GLM-5.2 | Step 3 |
|---|---|---|
| Provider | Z.ai (Zhipu) | StepFun |
| Noometry Index | 51.1 | 40.5 |
| Rank | 44 | 149 |
| Context | 1M | — |
| Input $/M | $1.40 | — |
| Output $/M | $4.40 | — |
| Weights | Open | Open |

## Coding

- GLM-5.2: 51.3 (#41)
- Step 3: 40.1 (#147)

| Benchmark | GLM-5.2 | Step 3 |
|---|---|---|
| LMArena Coding | 1485 | 1367 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| LMArena WebDev | 1603 | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| ALE-Bench | 1,047 | — |

## Agentic & Tool Use

- GLM-5.2: 32.4 (#63)
- Step 3: —

| Benchmark | GLM-5.2 | Step 3 |
|---|---|---|
| APEX-Agents | 45.2% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |

## Reasoning

- GLM-5.2: 42.3 (#52)
- Step 3: 28.4 (#105)

| Benchmark | GLM-5.2 | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 62.6% | 62.3% |
| LMArena Hard Prompts | 1480 | 1355 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| NYT Connections (extended) | 74.3% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| Chess Puzzles | 21% | — |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 93.6% | — |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |
| Epoch Capabilities Index | 151.78 | — |

## Math

- GLM-5.2: 55.7 (#43)
- Step 3: 37.6 (#148)

| Benchmark | GLM-5.2 | Step 3 |
|---|---|---|
| LMArena Math | 1482 | 1366 |
| 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% | — |

## Knowledge

- GLM-5.2: 57.1 (#40)
- Step 3: 36.8 (#164)

| Benchmark | GLM-5.2 | Step 3 |
|---|---|---|
| LMArena Expert | 1486 | 1333 |
| GPQA Diamond | 91.9% | — |
| SimpleQA Verified | 34.2% | — |

## Multimodal

- GLM-5.2: —
- Step 3: 35.5 (#86)

| Benchmark | GLM-5.2 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- GLM-5.2: 55.8 (#26)
- Step 3: 46.3 (#159)

| Benchmark | GLM-5.2 | Step 3 |
|---|---|---|
| LMArena Non-English | 1459 | 1327 |
| LMArena Chinese | 1519 | 1397 |
| LMArena German | 1468 | 1371 |
| LMArena Korean | 1445 | 1269 |
| LMArena Russian | 1466 | 1331 |
| LMArena Spanish | 1477 | 1371 |
| LMArena French | 1479 | — |
| LMArena Japanese | 1451 | — |

## Instruction Following

- GLM-5.2: 76.9 (#34)
- Step 3: 70.4 (#164)

| Benchmark | GLM-5.2 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1465 | 1332 |

## Long Context

- GLM-5.2: 45.3 (#43)
- Step 3: 40.3 (#157)

| Benchmark | GLM-5.2 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1479 | 1326 |

## Writing & Preference

- GLM-5.2: 70.4 (#21)
- Step 3: 54.3 (#151)

| Benchmark | GLM-5.2 | Step 3 |
|---|---|---|
| LMArena Text | 1470 | 1350 |
| LMArena Creative Writing | 1462 | 1321 |
| LMArena Multi-Turn | 1469 | 1341 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |

## FAQ

### Is GLM-5.2 better than Step 3?

GLM-5.2 is the stronger model overall, scoring 51.1 to 40.5 on the Noometry Index.

### Is GLM-5.2 or Step 3 better for coding?

GLM-5.2 scores higher on coding benchmarks: 51.3 versus 40.1 in the Noometry coding category.

### How many benchmarks do GLM-5.2 and Step 3 share?

16 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Step 3 has 17.