# GLM-5.1 vs Hy3

> GLM-5.1 is the stronger model overall, scoring 47.6 to 43.6 on the Noometry Index. Hy3 costs 9.3× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-hy3
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Hy3 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.1 leads 55.0 to 40.2.
- The biggest single-benchmark swing is NYT Connections (extended): 77.7% for GLM-5.1 and 41.2% for Hy3.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Hy3 accepts more context: 262K tokens versus 200K.

## Snapshot

| | GLM-5.1 | Hy3 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Tencent |
| Noometry Index | 47.6 | 43.6 |
| Rank | 51 | 79 |
| Context | 200K | 262K |
| Input $/M | $1.40 | $0.13 |
| Output $/M | $4.40 | $0.53 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.5 (#52)
- Hy3: 46.6 (#60)

| Benchmark | GLM-5.1 | Hy3 |
|---|---|---|
| LMArena WebDev | 1509 | 1509 |
| LMArena Coding | 1486 | 1465 |
| SWE-bench Verified | 74.2% | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- Hy3: —

| Benchmark | GLM-5.1 | Hy3 |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- Hy3: 25.0 (#134)

| Benchmark | GLM-5.1 | Hy3 |
|---|---|---|
| NYT Connections (extended) | 77.7% | 41.2% |
| LMArena Hard Prompts | 1472 | 1449 |
| SimpleBench | 55.1% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| Epoch Capabilities Index | 149.86 | — |

## Math

- GLM-5.1: 49.0 (#48)
- Hy3: 37.4 (#98)

| Benchmark | GLM-5.1 | Hy3 |
|---|---|---|
| LMArena Math | 1472 | 1475 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- Hy3: 40.2 (#108)

| Benchmark | GLM-5.1 | Hy3 |
|---|---|---|
| LMArena Expert | 1477 | 1461 |
| GPQA Diamond | 89.9% | — |
| SimpleQA Verified | 34% | — |

## Multilingual

- GLM-5.1: 55.2 (#34)
- Hy3: 53.7 (#60)

| Benchmark | GLM-5.1 | Hy3 |
|---|---|---|
| LMArena Non-English | 1448 | 1427 |
| LMArena Chinese | 1516 | 1496 |
| LMArena French | 1478 | 1461 |
| LMArena Korean | 1423 | 1390 |
| LMArena Russian | 1453 | 1435 |
| LMArena Spanish | 1467 | 1448 |
| LMArena German | 1466 | — |
| LMArena Japanese | 1436 | — |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- Hy3: 75.3 (#68)

| Benchmark | GLM-5.1 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1451 | 1425 |

## Long Context

- GLM-5.1: 44.9 (#51)
- Hy3: 44.1 (#70)

| Benchmark | GLM-5.1 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1467 | 1443 |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- Hy3: 62.5 (#75)

| Benchmark | GLM-5.1 | Hy3 |
|---|---|---|
| LMArena Text | 1462 | 1442 |
| LMArena Creative Writing | 1454 | 1399 |
| LMArena Multi-Turn | 1473 | 1436 |
| EQ-Bench Creative Writing | 1592 | — |

## FAQ

### Is GLM-5.1 better than Hy3?

GLM-5.1 is the stronger model overall, scoring 47.6 to 43.6 on the Noometry Index. Hy3 costs 9.3× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

### Which is cheaper, GLM-5.1 or Hy3?

Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5.1 or Hy3 better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 46.6 in the Noometry coding category.

### Which has the bigger context window?

Hy3 does, with 262K tokens against 200K.

### How many benchmarks do GLM-5.1 and Hy3 share?

17 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Hy3 has 17.