Model comparison
GLM-4.5V vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 44.6 to 39.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
TencentSummary
- The widest gap is in math, where Hy4 preview leads 54.5 to 34.7.
- GLM-4.5V is cheaper at $0.60 / $1.80 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 64K.
Side by side
| GLM-4.5V | Hy4 preview | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Tencent |
| Noometry Index | 39.2 | 44.6 |
| Released | 2025-08-11 | 2026-08-28 |
| Weights | Open | Open |
| Context window | 64K | 1.05M |
| Max output | 16K | 64K |
| Input $ / M tokens | $0.60 | $0.83 |
| Output $ / M tokens | $1.80 | $2.50 |
| Results tracked | 15 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
GLM-4.5V: 38.9 (#152), Hy4 preview: 51.4 (#36)
| Benchmark | GLM-4.5V | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1633 |
| LMArena Coding | 1347 | — |
Reasoning Hy4 preview leads
GLM-4.5V: 26.5 (#118), Hy4 preview: 30.6 (#75)
| Benchmark | GLM-4.5V | Hy4 preview |
|---|---|---|
| Kagi LLM Benchmark | 59.8% | — |
| NYT Connections (extended) | — | 68.2% |
| LMArena Hard Prompts | 1335 | — |
Math Hy4 preview leads
GLM-4.5V: 34.7 (#157), Hy4 preview: 54.5 (#37)
| Benchmark | GLM-4.5V | Hy4 preview |
|---|---|---|
| ProofBench | — | 75% |
| LMArena Math | 1353 | — |
Knowledge Not comparable
GLM-4.5V: 36.8 (#155), Hy4 preview: —
| Benchmark | GLM-4.5V | Hy4 preview |
|---|---|---|
| LMArena Expert | 1353 | — |
Multimodal Not comparable
GLM-4.5V: 33.6 (#86), Hy4 preview: —
| Benchmark | GLM-4.5V | Hy4 preview |
|---|---|---|
| LMArena Vision | 1154 | — |
Multilingual Not comparable
GLM-4.5V: 44.9 (#172), Hy4 preview: —
| Benchmark | GLM-4.5V | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1304 | — |
| LMArena Chinese | 1338 | — |
| LMArena Russian | 1299 | — |
| LMArena Spanish | 1335 | — |
Instruction Following Not comparable
GLM-4.5V: 69.4 (#170), Hy4 preview: —
| Benchmark | GLM-4.5V | Hy4 preview |
|---|---|---|
| LMArena Instruction Following | 1311 | — |
Long Context Not comparable
GLM-4.5V: 39.6 (#166), Hy4 preview: —
| Benchmark | GLM-4.5V | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 1305 | — |
Writing & Preference Not comparable
GLM-4.5V: 52.7 (#162), Hy4 preview: —
| Benchmark | GLM-4.5V | Hy4 preview |
|---|---|---|
| LMArena Text | 1333 | — |
| LMArena Creative Writing | 1295 | — |
| LMArena Multi-Turn | 1333 | — |
Frequently asked questions
Is GLM-4.5V better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 44.6 to 39.2 on the Noometry Index.
Which is cheaper, GLM-4.5V or Hy4 preview?
GLM-4.5V is cheaper. It lists at $0.60 per million input tokens and $1.80 per million output tokens; Hy4 preview lists at $0.83 and $2.50.
Is GLM-4.5V or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.4 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 64K.
How many benchmarks do GLM-4.5V and Hy4 preview share?
0 benchmarks have published results for both models. GLM-4.5V has 15 scored results on Noometry and Hy4 preview has 3.