Compare Models
Select models (max 5)
GPT-5.6 SolClaude Haiku 5.5
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 58.01%±1.02 | 54.31%±1.41 |
| Legal Research BenchAgentic US legal research | 48.08%±3.47 | 43.27%±3.44 |
| Finance Agent (v2)Core financial analyst tasks | 53.76%±0.85 | 54.14%±2.13 |
| Tax Agent BenchAgentic US corporate tax research | 31.09%±3.34 | 31.92%±3.35 |
| MedCodeMedical billing code support | 43.97%±2.26 | 51.54%±2.17 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 20.00%±4.82 | 10.00%±3.61 |
| Code MigrationRewriting programs in new languages | 52.92%±4.35 | 44.57%±4.23 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 37.88%±0.00 | 35.35%±2.20 |
| Vibe Code Bench v1.1Building web apps from scratch | 80.50%±3.72 | 90.44%±1.73 |
Benchmarks
Vals Index *
GPT-5.6 Sol
0.00%± 1.02
(45/45)Claude Haiku 5.5
0.00%± 1.41
(45/45)Legal Research Bench *
GPT-5.6 Sol
0.00%± 3.47
(75/75)Claude Haiku 5.5
0.00%± 3.44
(75/75)Finance Agent (v2) *
GPT-5.6 Sol
0.00%± 0.85
(76/76)Claude Haiku 5.5
0.00%± 2.13
(76/76)Tax Agent Bench *
GPT-5.6 Sol
0.00%± 3.34
(67/67)Claude Haiku 5.5
0.00%± 3.35
(67/67)MedCode *
GPT-5.6 Sol
0.00%± 2.26
(106/106)Claude Haiku 5.5
0.00%± 2.17
(106/106)Terminal-Bench Science
GPT-5.6 Sol
0.00%± 4.82
(39/39)Claude Haiku 5.5
0.00%± 3.61
(39/39)Code Migration *
GPT-5.6 Sol
0.00%± 4.35
(75/75)Claude Haiku 5.5
0.00%± 4.23
(75/75)Terminal-Bench 4.0
GPT-5.6 Sol
0.00%± 0.00
(45/45)Claude Haiku 5.5
0.00%± 2.20
(45/45)Vibe Code Bench v1.1 *
GPT-5.6 Sol
0.00%± 3.72
(110/110)Claude Haiku 5.5
0.00%± 1.73
(110/110)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-07
Comparison by Industry
Model performance on different sections of the economy.
Legal
45.85%
vs.22.26%
Finance
59.85%
vs.48.36%
Healthcare
64.60%
vs.70.54%
Math
83.00%
vs.86.00%
Science
41.48%
vs.38.50%
Academic
91.05%
vs.N/A
Education
52.56%
vs.45.78%
Coding
57.43%
vs.40.09%
Cyber
53.42%
vs.40.60%
Social Mobility
66.51%
vs.63.19%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$14.24
$2.991
Cost / TestVals Index
$14.24
vs.$2.991
Input Cost/ 1M Tokens
$4.00
vs.$0.10
Input Cache Write/ 1M Tokens
$5.00
vs.$0.125
Input Cache Read/ 1M Tokens
$0.40
vs.$0.01
Output Cost/ 1M Tokens
$20.00
vs.$0.50
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | OpenAI | Anthropic |
| Latency | 2242.74s | 2836.53s |
| Cost (In/Out) | $4 / $20 | $0.1 / $0.5 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |