Compare Models
Select models (max 7)
Qwen 3 Max ThinkingClaude Fable 5.2
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 71.31%±0.96 |
| Legal Research BenchAgentic US legal research | N/A | 46.15%±3.46 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 69.47%±1.98 |
| Tax Agent BenchAgentic US corporate tax research | N/A | 32.09%±3.37 |
| MedCodeMedical billing code support | 31.37%±1.89 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | N/A | 55.71%±5.98 |
| Code Migration v1.1Rewriting programs in new languages | N/A | 83.27%±3.12 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 65.15%±2.31 |
| Vibe Code Bench v1.1Building web apps from scratch | N/A | 93.77%±1.15 |
Benchmarks
Vals Index *
Qwen 3 Max Thinking
N/AClaude Fable 5.2
0.00%± 0.96
(36/36)Legal Research Bench *
Qwen 3 Max Thinking
N/AClaude Fable 5.2
0.00%± 3.46
(93/93)Finance Agent v2.1 *
Qwen 3 Max Thinking
N/AClaude Fable 5.2
0.00%± 1.98
(39/39)Tax Agent Bench *
Qwen 3 Max Thinking
N/AClaude Fable 5.2
0.00%± 3.37
(84/84)MedCode *
Qwen 3 Max Thinking
0.00%± 1.89
(107/107)Claude Fable 5.2
N/ATerminal-Bench-Science
Qwen 3 Max Thinking
N/AClaude Fable 5.2
0.00%± 5.98
(45/45)Code Migration v1.1 *
Qwen 3 Max Thinking
N/AClaude Fable 5.2
0.00%± 3.12
(30/30)Terminal-Bench 4.0
Qwen 3 Max Thinking
N/AClaude Fable 5.2
0.00%± 2.31
(63/63)Vibe Code Bench v1.1 *
Qwen 3 Max Thinking
N/AClaude Fable 5.2
0.00%± 1.15
(127/127)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
•2026-11-09
Comparison by Industry
Model performance on different sections of the economy.
Legal
N/A
vs.41.71%
Finance
N/A
vs.59.65%
Healthcare
52.04%
vs.N/A
Math
N/A
vs.100.00%
Science
N/A
vs.63.74%
Academic
84.91%
vs.N/A
Coding
N/A
vs.64.70%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$17.94
Cost / TestVals Index
N/A
vs.$17.94
Input Cost/ 1M Tokens
$1.20
vs.$8.00
Input Cache Write/ 1M Tokens
N/A
vs.$10.00
Input Cache Read/ 1M Tokens
N/A
vs.$0.20
Output Cost/ 1M Tokens
$6.00
vs.$40.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Alibaba | Anthropic |
| Latency | N/A | 2621.82s |
| Cost (In/Out) | $1.2 / $6 | $8 / $40 |
| Context Window | 256k | 1M |
| Max Output Token | 32k | 128k |
| Input Modality |