Compare Models
Select models (max 7)
Qwen 3.6 Max PreviewGemini 4 Hydrogen
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 68.49%±0.99 |
| Legal Research BenchAgentic US legal research | N/A | 53.85%±3.46 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 65.12%±2.04 |
| Tax Agent BenchAgentic US corporate tax research | N/A | 52.30%±3.60 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 54.04%±3.31 |
| Vibe Code Bench v1.1Building web apps from scratch | N/A | 87.78%±2.29 |
Benchmarks
Vals Index *
Qwen 3.6 Max Preview
N/AGemini 4 Hydrogen
0.00%± 0.99
(37/37)Legal Research Bench *
Qwen 3.6 Max Preview
N/AGemini 4 Hydrogen
0.00%± 3.46
(94/94)Finance Agent v2.1 *
Qwen 3.6 Max Preview
N/AGemini 4 Hydrogen
0.00%± 2.04
(40/40)Tax Agent Bench *
Qwen 3.6 Max Preview
N/AGemini 4 Hydrogen
0.00%± 3.60
(85/85)Terminal-Bench 4.0
Qwen 3.6 Max Preview
N/AGemini 4 Hydrogen
0.00%± 3.31
(64/64)Vibe Code Bench v1.1 *
Qwen 3.6 Max Preview
N/AGemini 4 Hydrogen
0.00%± 2.29
(128/128)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
•2026-11-11
Comparison by Industry
Model performance on different sections of the economy.
Legal
N/A
vs.32.55%
Finance
N/A
vs.64.41%
Coding
72.80%
vs.70.91%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$9.838
Cost / TestVals Index
N/A
vs.$9.838
Input Cost/ 1M Tokens
$1.30
vs.$1.50
Input Cache Write/ 1M Tokens
$1.625
vs.N/A
Input Cache Read/ 1M Tokens
$0.13
vs.$0.15
Output Cost/ 1M Tokens
$7.80
vs.$7.50
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Alibaba | Google |
| Latency | N/A | 1924.73s |
| Cost (In/Out) | $1.3 / $7.8 | $1.5 / $7.5 |
| Context Window | 262k | 1M |
| Max Output Token | 66k | 1M |
| Input Modality |