Compare Models
Select models (max 7)
Claude Opus 4.8GPT-6 Sol
| Legal Research BenchAgentic US legal research | 43.75%±3.45 | 28.85%±3.15 |
| Tax Agent BenchAgentic US corporate tax research | 30.00%±3.30 | 15.00%±2.58 |
| MedCodeMedical billing code support | 53.22%±2.17 | 47.07%±2.12 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 4.29%±2.44 | 30.00%±5.52 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 23.23%±1.34 | 44.44%±3.54 |
| Vibe Code Bench v1.1Building web apps from scratch | 82.72%±3.08 | 87.82%±2.53 |
Benchmarks
Legal Research Bench *
Claude Opus 4.8
0.00%± 3.45
(98/98)GPT-6 Sol
0.00%± 3.15
(98/98)Tax Agent Bench *
Claude Opus 4.8
0.00%± 3.30
(89/89)GPT-6 Sol
0.00%± 2.58
(89/89)MedCode *
Claude Opus 4.8
0.00%± 2.17
(107/107)GPT-6 Sol
0.00%± 2.12
(107/107)Terminal-Bench-Science
Claude Opus 4.8
0.00%± 2.44
(47/47)GPT-6 Sol
0.00%± 5.52
(47/47)Terminal-Bench 4.0
Claude Opus 4.8
0.00%± 1.34
(68/68)GPT-6 Sol
0.00%± 3.54
(68/68)Vibe Code Bench v1.1 *
Claude Opus 4.8
0.00%± 3.08
(132/132)GPT-6 Sol
0.00%± 2.53
(132/132)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
63.66%
vs.28.85%
Finance
58.52%
vs.15.00%
Healthcare
69.49%
vs.64.55%
Math
N/A
vs.83.00%
Science
4.29%
vs.45.00%
Academic
89.53%
vs.N/A
Coding
57.10%
vs.54.22%
Cyber
N/A
vs.54.25%
Social Mobility
68.13%
vs.59.62%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
N/A
Cost / TestVals Index
N/A
vs.N/A
Input Cost/ 1M Tokens
$5.00
vs.$2.00
Input Cache Write/ 1M Tokens
$6.25
vs.$2.50
Input Cache Read/ 1M Tokens
$0.50
vs.$0.20
Output Cost/ 1M Tokens
$25.00
vs.$10.00
Model Metadata
Basic information about each model.
| Model provider | ||
| Latency | N/A | N/A |
| Cost (In/Out) | $5 / $25 | $2 / $10 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |