Compare Models
Select models (max 7)
Hy4 FlashQwen 4 Max
| Vals IndexGDP-weighted benchmark | 50.78%±1.08 | 63.20%±1.01 |
| Legal Research BenchAgentic US legal research | 38.46%±3.38 | 41.35%±3.42 |
| Finance Agent v2.1Core financial analyst tasks | 60.81%±2.08 | 66.68%±2.02 |
| Tax Agent BenchAgentic US corporate tax research | 23.25%±3.04 | 40.35%±3.54 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 15.15%±1.75 | 48.48%±0.88 |
| Vibe Code Bench v1.1Building web apps from scratch | 74.84%±3.86 | 86.66%±2.27 |
Benchmarks
Vals Index *
Hy4 Flash
0.00%± 1.08
(39/39)Qwen 4 Max
0.00%± 1.01
(39/39)Legal Research Bench *
Hy4 Flash
0.00%± 3.38
(96/96)Qwen 4 Max
0.00%± 3.42
(96/96)Finance Agent v2.1 *
Hy4 Flash
0.00%± 2.08
(42/42)Qwen 4 Max
0.00%± 2.02
(42/42)Tax Agent Bench *
Hy4 Flash
0.00%± 3.04
(87/87)Qwen 4 Max
0.00%± 3.54
(87/87)Terminal-Bench 4.0
Hy4 Flash
0.00%± 1.75
(66/66)Qwen 4 Max
0.00%± 0.88
(66/66)Vibe Code Bench v1.1 *
Hy4 Flash
0.00%± 3.86
(130/130)Qwen 4 Max
0.00%± 2.27
(130/130)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
Comparison by Industry
Model performance on different sections of the economy.
Legal
21.94%
vs.31.30%
Finance
49.01%
vs.59.29%
Coding
44.99%
vs.67.57%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$0.07
$9.33
Cost / TestVals Index
$0.07
vs.$9.33
Input Cost/ 1M Tokens
$0.07
vs.$1.50
Input Cache Read/ 1M Tokens
$0.003
vs.$0.075
Output Cost/ 1M Tokens
$0.281
vs.$4.50
Model Metadata
Basic information about each model.
| Model provider | ||
| Latency | 1019.22s | 3879.45s |
| Cost (In/Out) | $0.07 / $0.281 | $1.5 / $4.5 |
| Context Window | 1M | 1M |
| Max Output Token | 66k | 262k |
| Input Modality |