Compare Models

Select models (max 7)
Claude Fable 5.1GPT-6 Astra
Benchmarks

Vals Index *

Claude Fable 5.1
N/A
GPT-6 Astra
0.00%± 1.10
(38/38)

Legal Research Bench *

Claude Fable 5.1
0.00%± 3.46
(95/95)
GPT-6 Astra
0.00%± 3.40
(95/95)

Finance Agent v2.1 *

Claude Fable 5.1
N/A
GPT-6 Astra
0.00%± 2.12
(41/41)

Tax Agent Bench *

Claude Fable 5.1
0.00%± 3.61
(86/86)
GPT-6 Astra
0.00%± 2.92
(86/86)

MedCode *

Claude Fable 5.1
0.00%± 2.17
(107/107)
GPT-6 Astra
0.00%± 2.13
(107/107)

Terminal-Bench-Science

Claude Fable 5.1
0.00%± 5.90
(45/45)
GPT-6 Astra
0.00%± 5.82
(45/45)

Code Migration v1.1 *

Claude Fable 5.1
N/A
GPT-6 Astra
0.00%± 2.34
(30/30)

Terminal-Bench 4.0

Claude Fable 5.1
0.00%± 3.31
(65/65)
GPT-6 Astra
0.00%± 4.40
(65/65)

Vibe Code Bench v1.1 *

Claude Fable 5.1
0.00%± 1.57
(129/129)
GPT-6 Astra
0.00%± 2.17
(129/129)

Overall performance

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

2026-11-15

Comparison by Industry

Model performance on different sections of the economy.

Legal
73.08%
38.07%
Finance
68.56%
51.28%
Healthcare
72.40%
68.20%
Math
100.00%
99.00%
Science
31.19%
54.65%
Academic
92.15%
N/A
Coding
65.63%
63.10%
Cyber
46.66%
48.97%
Social Mobility
75.31%
67.53%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$21.28
Cost / TestVals Index
N/A
$21.28
Input Cost/ 1M Tokens
$10.00
$10.00
Input Cache Write/ 1M Tokens
$12.50
$12.50
Input Cache Read/ 1M Tokens
$0.25
$1.00
Output Cost/ 1M Tokens
$50.00
$50.00

Model Metadata

Basic information about each model.

Model provider
AnthropicAnthropic
OpenAIOpenAI
LatencyN/A2018.88s
Cost (In/Out)$10 / $50$10 / $50
Context Window1M1M
Max Output Token128k128k
Input Modality