Compare Models
Select models (max 5)
Hy4 PreviewGLM 5.2
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 49.94%±1.15 | N/A |
| Legal Research BenchAgentic US legal research | 45.19%±3.46 | 31.25%±3.22 |
| Finance Agent (v2)Core financial analyst tasks | 55.06%±0.31 | 49.70%±0.88 |
| Tax Agent BenchAgentic US corporate tax research | 63.71%±3.26 | N/A |
| MedCodeMedical billing code support | 43.25%±2.13 | 40.77%±2.17 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 1.43%±1.43 | N/A |
| Code MigrationRewriting programs in new languages | 47.43%±4.27 | 37.87%±4.14 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 8.08%±1.34 | N/A |
| Vibe Code Bench v1.1Building web apps from scratch | 77.48%±4.04 | 63.96%±4.79 |
Benchmarks
Vals Index *
Hy4 Preview
0.00%± 1.15
(43/43)GLM 5.2
N/ALegal Research Bench *
Hy4 Preview
0.00%± 3.46
(73/73)GLM 5.2
0.00%± 3.22
(73/73)Finance Agent (v2) *
Hy4 Preview
0.00%± 0.31
(74/74)GLM 5.2
0.00%± 0.88
(74/74)Tax Agent Bench *
Hy4 Preview
0.00%± 3.26
(65/65)GLM 5.2
N/AMedCode *
Hy4 Preview
0.00%± 2.13
(104/104)GLM 5.2
0.00%± 2.17
(104/104)Terminal-Bench Science
Hy4 Preview
0.00%± 1.43
(38/38)GLM 5.2
N/ACode Migration *
Hy4 Preview
0.00%± 4.27
(73/73)GLM 5.2
0.00%± 4.14
(73/73)Terminal-Bench 4.0
Hy4 Preview
0.00%± 1.34
(43/43)GLM 5.2
N/AVibe Code Bench v1.1 *
Hy4 Preview
0.00%± 4.04
(108/108)GLM 5.2
0.00%± 4.79
(108/108)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-02
Comparison by Industry
Model performance on different sections of the economy.
Legal
46.04%
vs.40.80%
Finance
58.95%
vs.61.52%
Healthcare
63.42%
vs.62.15%
Math
75.00%
vs.N/A
Science
35.34%
vs.N/A
Academic
N/A
vs.86.16%
Coding
38.47%
vs.49.95%
Cyber
33.82%
vs.0.00%
Social Mobility
68.61%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$1.439
N/A
Cost / TestVals Index
$1.439
vs.N/A
Input Cost/ 1M Tokens
$0.834
vs.$1.40
Input Cache Read/ 1M Tokens
$0.042
vs.$0.26
Output Cost/ 1M Tokens
$2.501
vs.$4.40
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Openrouter | zAI |
| Latency | 3656.53s | N/A |
| Cost (In/Out) | $0.834 / $2.501 | $1.4 / $4.4 |
| Context Window | 1M | 1M |
| Max Output Token | 64k | 131k |
| Input Modality |