Compare Models

Select models (max 7)
Claude Opus 5.5GPT-6 Astra
Benchmarks

Vals Index *

Claude Opus 5.5
0.00%± 1.00
(41/41)
GPT-6 Astra
0.00%± 1.10
(41/41)

Legal Research Bench *

Claude Opus 5.5
0.00%± 3.48
(98/98)
GPT-6 Astra
0.00%± 3.40
(98/98)

Finance Agent v2.1 *

Claude Opus 5.5
0.00%± 2.05
(44/44)
GPT-6 Astra
0.00%± 2.12
(44/44)

Tax Agent Bench *

Claude Opus 5.5
0.00%± 3.58
(89/89)
GPT-6 Astra
0.00%± 2.92
(89/89)

MedCode *

Claude Opus 5.5
0.00%± 2.27
(107/107)
GPT-6 Astra
0.00%± 2.13
(107/107)

Terminal-Bench-Science

Claude Opus 5.5
0.00%± 6.01
(47/47)
GPT-6 Astra
0.00%± 5.82
(47/47)

Code Migration v1.1 *

Claude Opus 5.5
0.00%± 3.21
(30/30)
GPT-6 Astra
0.00%± 2.34
(30/30)

Terminal-Bench 4.0

Claude Opus 5.5
0.00%± 0.00
(68/68)
GPT-6 Astra
0.00%± 4.40
(68/68)

Vibe Code Bench v1.1 *

Claude Opus 5.5
0.00%± 1.53
(132/132)
GPT-6 Astra
0.00%± 2.17
(132/132)

Overall performance

Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax

2026-11-16

Comparison by Industry

Model performance on different sections of the economy.

Legal
43.93%
38.07%
Finance
72.05%
51.28%
Healthcare
70.61%
68.20%
Math
100.00%
99.00%
Science
47.63%
54.65%
Education
91.30%
N/A
Coding
64.45%
63.10%
Cyber
55.35%
48.97%
Social Mobility
73.52%
67.53%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
$24.77
$21.28
Cost / TestVals Index
$24.77
$21.28
Input Cost/ 1M Tokens
$4.00
$10.00
Input Cache Write/ 1M Tokens
$5.00
$12.50
Input Cache Read/ 1M Tokens
$0.20
$1.00
Output Cost/ 1M Tokens
$20.00
$50.00

Model Metadata

Basic information about each model.

Model provider
AnthropicAnthropic
OpenAIOpenAI
Latency5071.09s2018.88s
Cost (In/Out)$4 / $20$10 / $50
Context Window1M1M
Max Output Token128k128k
Input Modality