Compare Models
Select models (max 7)
Claude Haiku 4.5 (Thinking)Hy4
| Vals IndexGDP-weighted benchmark | N/A | 59.35%±1.08 |
| Legal Research BenchAgentic US legal research | 10.58%±2.14 | 41.35%±3.42 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 64.70%±2.05 |
| Tax Agent BenchAgentic US corporate tax research | 5.86%±1.54 | 34.40%±3.30 |
| MedCodeMedical billing code support | 32.68%±2.00 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 39.39%±0.88 |
| Vibe Code Bench v1.1Building web apps from scratch | 11.39%±3.13 | 81.01%±3.55 |
Benchmarks
Vals Index *
Claude Haiku 4.5 (Thinking)
N/AHy4
0.00%± 1.08
(33/33)Legal Research Bench *
Claude Haiku 4.5 (Thinking)
0.00%± 2.14
(90/90)Hy4
0.00%± 3.42
(90/90)Finance Agent v2.1 *
Claude Haiku 4.5 (Thinking)
N/AHy4
0.00%± 2.05
(36/36)Tax Agent Bench *
Claude Haiku 4.5 (Thinking)
0.00%± 1.54
(81/81)Hy4
0.00%± 3.30
(81/81)MedCode *
Claude Haiku 4.5 (Thinking)
0.00%± 2.00
(107/107)Hy4
N/ATerminal-Bench 4.0
Claude Haiku 4.5 (Thinking)
N/AHy4
0.00%± 0.88
(60/60)Vibe Code Bench v1.1 *
Claude Haiku 4.5 (Thinking)
0.00%± 3.13
(124/124)Hy4
0.00%± 3.55
(124/124)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
45.91%
vs.26.92%
Finance
45.19%
vs.55.09%
Healthcare
58.95%
vs.N/A
Academic
65.67%
vs.N/A
Coding
29.79%
vs.60.20%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$1.72
Cost / TestVals Index
N/A
vs.$1.72
Input Cost/ 1M Tokens
$1.00
vs.$0.834
Input Cache Write/ 1M Tokens
$1.25
vs.N/A
Input Cache Read/ 1M Tokens
$0.10
vs.$0.042
Output Cost/ 1M Tokens
$5.00
vs.$2.501
Model Metadata
Basic information about each model.
| Model provider | ||
| Latency | N/A | 3091.47s |
| Cost (In/Out) | $1 / $5 | $0.834 / $2.501 |
| Context Window | 200k | 1M |
| Max Output Token | 64k | 66k |
| Input Modality |