Compare Models
Select models (max 7)
Qwen 4 MaxGemini 4 Hydrogen
| Vals IndexGDP-weighted benchmark | 63.20%±1.01 | 68.49%±0.99 |
| Legal Research BenchAgentic US legal research | 41.35%±3.42 | 53.85%±3.46 |
| Finance Agent v2.1Core financial analyst tasks | 66.68%±2.02 | 65.12%±2.04 |
| Tax Agent BenchAgentic US corporate tax research | 40.35%±3.54 | 52.30%±3.60 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 48.48%±0.88 | 54.04%±3.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 86.66%±2.27 | 87.78%±2.29 |
Benchmarks
Vals Index *
Qwen 4 Max
0.00%± 1.01
(38/38)Gemini 4 Hydrogen
0.00%± 0.99
(38/38)Legal Research Bench *
Qwen 4 Max
0.00%± 3.42
(95/95)Gemini 4 Hydrogen
0.00%± 3.46
(95/95)Finance Agent v2.1 *
Qwen 4 Max
0.00%± 2.02
(41/41)Gemini 4 Hydrogen
0.00%± 2.04
(41/41)Tax Agent Bench *
Qwen 4 Max
0.00%± 3.54
(86/86)Gemini 4 Hydrogen
0.00%± 3.60
(86/86)Terminal-Bench 4.0
Qwen 4 Max
0.00%± 0.88
(65/65)Gemini 4 Hydrogen
0.00%± 3.31
(65/65)Vibe Code Bench v1.1 *
Qwen 4 Max
0.00%± 2.27
(129/129)Gemini 4 Hydrogen
0.00%± 2.29
(129/129)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
31.30%
vs.32.55%
Finance
59.29%
vs.64.41%
Coding
67.57%
vs.70.91%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$9.33
$9.838
Cost / TestVals Index
$9.33
vs.$9.838
Input Cost/ 1M Tokens
$1.50
vs.$1.50
Input Cache Read/ 1M Tokens
$0.075
vs.$0.15
Output Cost/ 1M Tokens
$4.50
vs.$7.50
Model Metadata
Basic information about each model.
| Model provider | ||
| Latency | 3879.45s | 1924.73s |
| Cost (In/Out) | $1.5 / $4.5 | $1.5 / $7.5 |
| Context Window | 1M | 1M |
| Max Output Token | 262k | 1M |
| Input Modality |