Model comparison
GLM-4.6 vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 41.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
TencentSummary
- They share 18 benchmarks with published results for both. GLM-4.6 scores higher in 0 categories and Hy3 in 8 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.8 to 40.1.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- Hy3 accepts more context: 262K tokens versus 205K.
Side by side
| GLM-4.6 | Hy3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Tencent |
| Noometry Index | 41.4 | 44.2 |
| Released | 2025-09-30 | 2026-07-06 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.60 | $0.0825 |
| Output $ / M tokens | $2.20 | $0.33 |
| Results tracked | 29 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
GLM-4.6: 40.1 (#148), Hy3: 46.8 (#63)
| Benchmark | GLM-4.6 | Hy3 |
|---|---|---|
| LMArena WebDev | 1340 | 1508 |
| LMArena Coding | 1449 | 1464 |
| SWE-bench Verified (bash only) | 55.4% | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Not comparable
GLM-4.6: 32.3 (#66), Hy3: —
| Benchmark | GLM-4.6 | Hy3 |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning Hy3 leads
GLM-4.6: 23.7 (#172), Hy3: 26.1 (#136)
| Benchmark | GLM-4.6 | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1447 |
| Kagi LLM Benchmark | 47.4% | — |
| NYT Connections (extended) | — | 41.2% |
| CritPt | 1.1% | — |
Math Too close to call
GLM-4.6: 39.1 (#111), Hy3: 40.1 (#93)
| Benchmark | GLM-4.6 | Hy3 |
|---|---|---|
| LMArena Math | 1432 | 1475 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
GLM-4.6: 40.2 (#124), Hy3: 40.8 (#114)
| Benchmark | GLM-4.6 | Hy3 |
|---|---|---|
| LMArena Expert | 1431 | 1460 |
| Vectara Hallucination Rate | 9.5% | — |
Multilingual Too close to call
GLM-4.6: 53.5 (#66), Hy3: 53.5 (#65)
| Benchmark | GLM-4.6 | Hy3 |
|---|---|---|
| LMArena Non-English | 1426 | 1426 |
| LMArena Chinese | 1499 | 1493 |
| LMArena French | 1459 | 1461 |
| LMArena German | 1447 | 1439 |
| LMArena Japanese | 1393 | 1392 |
| LMArena Korean | 1400 | 1395 |
| LMArena Russian | 1419 | 1432 |
| LMArena Spanish | 1436 | 1456 |
Instruction Following Too close to call
GLM-4.6: 74.3 (#98), Hy3: 75.1 (#70)
| Benchmark | GLM-4.6 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1426 |
Long Context Too close to call
GLM-4.6: 43.4 (#94), Hy3: 44.1 (#75)
| Benchmark | GLM-4.6 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1422 | 1442 |
Writing & Preference Hy3 leads
GLM-4.6: 61.1 (#90), Hy3: 62.2 (#81)
| Benchmark | GLM-4.6 | Hy3 |
|---|---|---|
| LMArena Text | 1440 | 1439 |
| LMArena Creative Writing | 1411 | 1402 |
| LMArena Multi-Turn | 1427 | 1436 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 41.4 on the Noometry Index.
Which is cheaper, GLM-4.6 or Hy3?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 205K.
How many benchmarks do GLM-4.6 and Hy3 share?
18 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Hy3 has 19.