Compare Models

Select models (max 7)
Hy4 FlashQwen 4 Max
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

2026-11-16

Comparison by Industry

Model performance on different sections of the economy.

Legal
21.94%
31.30%
Finance
49.01%
59.29%
Coding
44.99%
67.57%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
$0.07
$9.33
Cost / TestVals Index
$0.07
$9.33
Input Cost/ 1M Tokens
$0.07
$1.50
Input Cache Read/ 1M Tokens
$0.003
$0.075
Output Cost/ 1M Tokens
$0.281
$4.50

Model Metadata

Basic information about each model.

Model provider
TencentOpenrouter
AlibabaAlibaba
Latency1019.22s3879.45s
Cost (In/Out)$0.07 / $0.281$1.5 / $4.5
Context Window1M1M
Max Output Token66k262k
Input Modality