Compare Models
Select models (max 5)
Qwen 3.8 MaxGrok 4.5
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 48.27%±1.34 | 44.72%±1.17 |
| Legal Research BenchAgentic US legal research | 47.60%±3.47 | 37.98%±3.37 |
| Finance Agent (v2)Core financial analyst tasks | 50.59%±0.58 | 48.35%±0.46 |
| Tax Agent BenchAgentic US corporate tax research | 65.96%±3.18 | 64.32%±3.16 |
| MedCodeMedical billing code support | 40.67%±2.03 | 43.29%±2.31 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 12.86%±4.03 | N/A |
| Code MigrationRewriting programs in new languages | 23.96%±4.31 | 36.60%±4.14 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 34.34%±3.94 | 8.59%±1.34 |
| Vibe Code Bench v1.1Building web apps from scratch | 64.70%±5.36 | 69.00%±4.48 |
Benchmarks
Vals Index *
Qwen 3.8 Max
0.00%± 1.34
(43/43)Grok 4.5
0.00%± 1.17
(43/43)Legal Research Bench *
Qwen 3.8 Max
0.00%± 3.47
(73/73)Grok 4.5
0.00%± 3.37
(73/73)Finance Agent (v2) *
Qwen 3.8 Max
0.00%± 0.58
(74/74)Grok 4.5
0.00%± 0.46
(74/74)Tax Agent Bench *
Qwen 3.8 Max
0.00%± 3.18
(65/65)Grok 4.5
0.00%± 3.16
(65/65)MedCode *
Qwen 3.8 Max
0.00%± 2.03
(104/104)Grok 4.5
0.00%± 2.31
(104/104)Terminal-Bench Science
Qwen 3.8 Max
0.00%± 4.03
(38/38)Grok 4.5
N/ACode Migration *
Qwen 3.8 Max
0.00%± 4.31
(73/73)Grok 4.5
0.00%± 4.14
(73/73)Terminal-Bench 4.0
Qwen 3.8 Max
0.00%± 3.94
(43/43)Grok 4.5
0.00%± 1.34
(43/43)Vibe Code Bench v1.1 *
Qwen 3.8 Max
0.00%± 5.36
(108/108)Grok 4.5
0.00%± 4.48
(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
47.21%
vs.45.62%
Finance
63.23%
vs.59.81%
Healthcare
62.81%
vs.65.09%
Math
58.00%
vs.31.00%
Science
18.37%
vs.N/A
Academic
90.11%
vs.81.31%
Education
51.25%
vs.34.97%
Coding
46.69%
vs.49.34%
Cyber
28.57%
vs.35.89%
Social Mobility
67.12%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$4.964
$2.459
Cost / TestVals Index
$4.964
vs.$2.459
Input Cost/ 1M Tokens
$2.00
vs.$2.00
Input Cache Write/ 1M Tokens
$2.50
vs.N/A
Input Cache Read/ 1M Tokens
$0.25
vs.$0.30
Output Cost/ 1M Tokens
$6.00
vs.$6.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Alibaba | SpaceXAI |
| Latency | 6070.72s | 944.20s |
| Cost (In/Out) | $2 / $6 | $2 / $6 |
| Context Window | 1M | 500k |
| Max Output Token | 128k | 500k |
| Input Modality |