Compare Models
Select models (max 5)
Qwen 3.6 Max PreviewClaude Sonnet 5.5
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 69.22%±0.96 |
| Legal Research BenchAgentic US legal research | N/A | 48.08%±3.47 |
| Finance Agent (v2)Core financial analyst tasks | N/A | 58.10%±0.67 |
| Tax Agent BenchAgentic US corporate tax research | N/A | 73.39%±2.98 |
| MedCodeMedical billing code support | N/A | 52.92%±2.12 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | N/A | 38.57%±5.86 |
| Code MigrationRewriting programs in new languages | N/A | 69.83%±4.26 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 53.03%±1.51 |
| Vibe Code Bench v1.1Building web apps from scratch | N/A | 92.39%±1.26 |
Benchmarks
Vals Index *
Qwen 3.6 Max Preview
N/AClaude Sonnet 5.5
0.00%± 0.96
(66/66)Legal Research Bench *
Qwen 3.6 Max Preview
N/AClaude Sonnet 5.5
0.00%± 3.47
(69/69)Finance Agent (v2) *
Qwen 3.6 Max Preview
N/AClaude Sonnet 5.5
0.00%± 0.67
(70/70)Tax Agent Bench *
Qwen 3.6 Max Preview
N/AClaude Sonnet 5.5
0.00%± 2.98
(61/61)MedCode *
Qwen 3.6 Max Preview
N/AClaude Sonnet 5.5
0.00%± 2.12
(102/102)Terminal-Bench Science
Qwen 3.6 Max Preview
N/AClaude Sonnet 5.5
0.00%± 5.86
(33/33)Code Migration *
Qwen 3.6 Max Preview
N/AClaude Sonnet 5.5
0.00%± 4.26
(69/69)Terminal-Bench 4.0
Qwen 3.6 Max Preview
N/AClaude Sonnet 5.5
0.00%± 1.51
(37/37)Vibe Code Bench v1.1 *
Qwen 3.6 Max Preview
N/AClaude Sonnet 5.5
0.00%± 1.26
(104/104)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-09-27
Comparison by Industry
Model performance on different sections of the economy.
Vals Index
N/A
vs.69.22%
Legal
N/A
vs.25.50%
Finance
N/A
vs.69.07%
Healthcare
N/A
vs.72.01%
Math
N/A
vs.100.00%
Science
N/A
vs.56.26%
Education
N/A
vs.51.77%
Coding
72.80%
vs.74.58%
Beta
N/A
vs.44.87%
Social Mobility
N/A
vs.67.19%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$20.80
Cost / TestVals Index
N/A
vs.$20.80
Input Cost/ 1M Tokens
$1.30
vs.$2.00
Input Cache Write/ 1M Tokens
$1.625
vs.$2.50
Input Cache Read/ 1M Tokens
$0.13
vs.$0.20
Output Cost/ 1M Tokens
$7.80
vs.$10.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Alibaba | Anthropic |
| Latency | N/A | 4207.12s |
| Cost (In/Out) | $1.3 / $7.8 | $2 / $10 |
| Context Window | 262k | 1M |
| Max Output Token | 66k | 128k |
| Input Modality |